Machine Learning
Convolutional Surrogate for 3D Discrete Fracture-Matrix Tensor Upscaling
Martin Špetlík and Jan Březina
Modeling groundwater flow in three-dimensional fractured crystalline media requires accounting for strong spatial heterogeneity induced by fractures. Fine-scale discrete fracture-
matrix (DFM) simulations can capture this complexity but are computationally expensive, especially when repeated evaluations are needed. To address this, we aim to employ a multilevel Monte Carlo (MLMC) framework in which numerical homogenization is used to upscale sub-resolution fracture effects when transitioning between accuracy levels. To reduce the cost of conventional 3D numerical homogenization, we develop a surrogate model that predicts the equivalent hydraulic conductivity tensor Keq from a voxelized 3D domain representing tensor-valued random fields of
matrix and fracture conductivities. Fracture size, orientation, and aperture are sampled from distributions informed by natural observations. The surrogate architecture combines a 3D convolutional neural network with feed-forward layers, enabling it to capture both local spatial features and global interactions. Three surrogates are trained on data generated by DFM simulations, each corresponding to a different fracture-to-
matrix conductivity contrast. Performance is evaluated across a wide range of fracture network parameters and
matrix-field correlation lengths. The trained models achieve high accuracy, with normalized root-mean-square errors below 0.22 across most test cases. Practical applicability is demonstrated by comparing numerically homogenized conductivities with surrogate predictions in two macro-scale problems: computing equivalent conductivity tensors and predicting
outflow from a constrained 3D domain. In both cases, surrogate-based upscaling preserves accuracy while substantially reducing computational cost, achieving speedups exceeding 100x when inference is performed on a GPU.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.IR
ReCQR: Incorporating conversational query rewriting to improve Multimodal Image Retrieval
Yuan Hu, ZhiYu Cao, PeiFeng Li et al. (+1 more)
With the rise of
multimodal learning, image
retrieval plays a crucial role in connecting visual information with natural
language queries. Existing image retrievers struggle with processing long texts and handling unclear user expressions. To address these issues, we introduce the conversational query rewriting (CQR) task into the image
retrieval domain and construct a dedicated multi-turn dialogue query rewriting
dataset. Built on full dialogue histories, CQR rewrites users' final queries into concise, semantically complete ones that are better suited for
retrieval. Specifically, We first leverage Large
Language Models (LLMs) to generate rewritten candidates at scale and employ an LLM-as-Judge mechanism combined with manual review to curate approximately 7,000 high-quality
multimodal dialogues, forming the ReCQR
dataset. Then We
benchmark several SOTA
multimodal models on the ReCQR
dataset to assess their performance on image
retrieval. Experimental results demonstrate that CQR not only significantly enhances the accuracy of traditional image
retrieval models, but also provides new directions and insights for modeling user queries in
multimodal systems.
Read the full abstract ▾
All authors Yuan Hu, ZhiYu Cao, PeiFeng Li, QiaoMing Zhu
Machine Learning · Cross-listed from cs.CL
Disentangling Direction and Magnitude in Transformer Representations: A Double Dissociation Through L2-Matched Perturbation Analysis
Mangadoddi Srikar Vardhan and Lekkala Sai Teja
Transformer hidden states encode information as high-dimensional vectors, yet whether direction (orientation in representational space) and magnitude (vector norm) serve distinct functional roles remains unclear. Studying Pythia-family models, we discover a striking cross-over dissociation: angular perturbations cause up to 42.9 more damage to
language modeling loss, while magnitude perturbations cause disproportionately more damage to syntactic processing (20.4% vs.1.6% accuracy drop on subject-verb agreement).This finding is enabled by L2-matched perturbation analysis, a methodology ensuring that an gular and magnitude perturbations achieve identical Euclidean displacements. Causal intervention reveals that angular damage flows substantially through the
attention pathways (28.4% loss recovery via
attention repair), while magnitude damage flows partly through the LayerNorm pathways(29.9% recovery via LayerNorm repair). These patterns replicate across scales within the Pythia architecture family. These findings provide evidence that direction and magnitude support partially distinct computational roles in LayerNorm based architectures. The direction preferentially affects attentional routing, while magnitude modulates processing intensity for fine-grained syntactic judgments. We find different patterns in RMSNorm-based architectures, suggesting that the dissociation depends on architectural choices. Our results refine the linear representation hypothesis and have implications for model editing and interpretability research
Read the full abstract ▾
Machine Learning
Augmenting Parameter-Efficient Pre-trained Language Models with Large Language Models
Saurabh Anand, Shubham Malaviya, Manish Shukla et al. (+1 more)
Training AI models in cybersecurity with help of vast
datasets offers significant opportunities to mimic real-world behaviors effectively. However, challenges like data drift and scarcity of labelled data lead to frequent updates of models and the risk of overfitting. To address these challenges, we used parameter-efficient fine-tuning techniques for pre-trained
language models wherein we combine compacters with various layer freezing strategies. To enhance the capabilities of these pre-trained
language models, in this work we introduce two strategies that use large
language models. In the first strategy, we utilize large
language models as data-labelling tools wherein they generate labels for unlabeled data. In the second strategy, large
language modes are utilized as fallback mechanisms for predictions having low confidence scores. We perform comprehensive experimental analysis on the proposed strategies on different downstream tasks specific to cybersecurity domain. We empirically demonstrate that by combining parameter-efficient pre-trained models with large
language models, we can improve the reliability and robustness of models, making them more suitable for real-world cybersecurity applications.
Read the full abstract ▾
All authors Saurabh Anand, Shubham Malaviya, Manish Shukla, Sachin Lodha
Machine Learning · Cross-listed from cs.AI
Scalable and Secure AI Inference in Healthcare: A Comparative Benchmarking of FastAPI and Triton Inference Server on Kubernetes
Ratul Ali
Efficient and scalable deployment of machine learning (ML) models is a prerequisite for modern production environments, particularly within regulated domains such as healthcare and pharmaceuticals. In these settings, systems must balance competing requirements, including minimizing inference latency for real-time clinical decision support, maximizing throughput for batch processing of medical records, and ensuring strict adherence to data
privacy standards such as HIPAA. This paper presents a rigorous benchmarking analysis comparing two prominent deployment paradigms: a lightweight, Python-based REST service using FastAPI, and a specialized, high-performance serving engine, NVIDIA Triton Inference Server. Leveraging a reference architecture for healthcare AI, we deployed a DistilBERT sentiment analysis model on Kubernetes to measure median (p50) and tail (p95) latency, as well as throughput, under controlled experimental conditions. Our results indicate a distinct trade-off. While FastAPI provides lower overhead for single-request workloads with a p50 latency of 22 ms, Triton achieves superior scalability through dynamic batching, delivering a throughput of 780 requests per second on a single NVIDIA T4 GPU, nearly double that of the baseline. Furthermore, we evaluate a hybrid architectural approach that utilizes FastAPI as a secure gateway for protected health information de-identification and Triton for backend inference. This study validates the hybrid model as a best practice for enterprise clinical AI and offers a blueprint for secure, high-availability deployments.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.IR
AI-assisted Protocol Information Extraction For Improved Accuracy and Efficiency in Clinical Trial Workflows
Ramtin Babaeipour, François Charest and Madison Wright
Increasing clinical trial protocol complexity, amendments, and challenges around knowledge management create significant burden for trial teams. Structuring protocol content into standard formats has the potential to improve efficiency, support documentation quality, and strengthen compliance. We evaluate an Artificial Intelligence (AI) system using generative LLMs with
Retrieval-Augmented Generation (RAG) for automated clinical trial protocol information extraction. We compare the extraction accuracy of our clinical-trial-specific RAG process against that of publicly available (standalone) LLMs. We also assess the operational impact of AI-assistance on simulated extraction Clinical Research Coordinator (CRC) workflows. Our RAG process shows higher extraction accuracy (89.0%) than standalone LLMs with fine-tuned
prompts (62.6%) against expert-supported reference annotations. In simulated extraction workflows, AI-assisted tasks are completed 40% faster, are rated as less cognitively demanding and are strongly preferred by users. While expert oversight remains essential, this suggests that AI-assisted extraction can enable protocol intelligence at scale, motivating the integration of similar methodologies into real-world clinical workflows to further validate its impact on feasibility, study start-up, and post-activation monitoring.
Read the full abstract ▾
Machine Learning
Distributional Reinforcement Learning for Condition-Based Maintenance of Multi-Pump Equipment
Takato Yasuno
Condition-Based Maintenance (CBM) signifies a paradigm shift from reactive to proactive equipment management strategies in modern industrial systems. Conventional time-based maintenance schedules frequently engender superfluous expenditures and unanticipated equipment failures. In contrast, CBM utilizes real-time equipment condition data to enhance maintenance timing and optimize resource allocation. The present paper proposes a novel distributional reinforcement learning approach for multi-equipment CBM using
Quantile Regression Deep Q-Networks (QR-DQN) with aging factor integration. The methodology employed in this study encompasses the concurrent administration of multiple pump units through three strategic scenarios. The implementation of safety-first, balanced, and cost-efficient approaches is imperative. Comprehensive experimental validation over 3,000 training episodes demonstrates significant performance improvements across all strategies. The Safety-First strategy demonstrates superior cost efficiency, with a return on investment (ROI) of 3.91, yielding 152% better performance than alternatives while requiring only 31% higher investment. The system exhibits 95.66% operational stability and immediate applicability to industrial environments.
Read the full abstract ▾
Machine Learning · Cross-listed from q-fin.ST
Exploring the Interpretability of Forecasting Models for Energy Balancing Market
Oskar Våle, Shiliang Zhang, Sabita Maharjan et al. (+1 more)
The balancing
market in the energy sector plays a critical role in physically and financially balancing the supply and demand. Modeling dynamics in the balancing
market can provide valuable insights and prognosis for power grid stability and secure energy supply. While complex machine learning models can achieve high accuracy, their black-box nature severely limits the model interpretability. In this paper, we explore the trade-off between model accuracy and interpretability for the energy balancing
market. Particularly, we take the example of
forecasting manual frequency restoration reserve (mFRR) activation price in the balancing
market using real
market data from different energy price zones. We explore the interpretability of mFRR
forecasting using two models: extreme gradient boosting (XGBoost) machine and explainable boosting machine (EBM). We also integrate the two models, and we
benchmark all the models against a baseline naive model. Our results show that EBM provides
forecasting accuracy comparable to XGBoost while yielding a considerable level of interpretability. Our analysis also underscores the challenge of accurately predicting the mFRR price for the instances when the activation price deviates significantly from the spot price. Importantly, EBM's interpretability features reveal insights into non-linear mFRR price drivers and regional
market dynamics. Our study demonstrates that EBM is a viable and valuable interpretable alternative to complex black-box AI models in the forecast for the balancing
market.
Read the full abstract ▾
All authors Oskar Våle, Shiliang Zhang, Sabita Maharjan, Gro Klæboe
Machine Learning · Cross-listed from quant-ph
Quantum Circuit-Based Learning Models: Bridging Quantum Computing and Machine Learning
Fan Fan, Yilei Shi, Mihai Datcu et al. (+5 more)
Machine Learning (ML) has been widely applied across numerous domains due to its ability to automatically identify informative patterns from data for various tasks. The availability of large-scale data and advanced computational power enables the development of sophisticated models and training strategies, leading to state-of-the-art performance, but it also introduces substantial challenges.
Quantum Computing (QC), which exploits
quantum mechanisms for computation, has attracted growing
attention and significant global investment as it may address these challenges. Consequently,
Quantum Machine Learning (QML), the integration of these two fields, has received increasing interest, with a notable rise in related studies in recent years. We are motivated to review these existing contributions regarding
quantum circuit-based learning models for classical data analysis and highlight the identified potentials and challenges of this technique. Specifically, we focus not only on QML models, both kernel-based and neural network-based, but also on recent explorations of their integration with classical machine learning layers within hybrid frameworks. Moreover, we examine both theoretical analysis and empirical findings to better understand their capabilities, and we also discuss the efforts on noise-resilient and hardware-efficient QML that could enhance its practicality under current hardware limitations. In addition, we cover several emerging paradigms for advanced
quantum circuit design and highlight the adaptability of QML across representative application domains. This study aims to provide an overview of the contributions made to bridge
quantum computing and machine learning, offering insights and guidance to support its future development and pave the way for broader adoption in the coming years.
Read the full abstract ▾
All authors Fan Fan, Yilei Shi, Mihai Datcu, Bertrand Le Saux, Luigi Iapichino, Francesca Bovolo, Silvia Liberata Ullo, Xiao Xiang Zhu
Machine Learning
Lightweight Edge Learning via Dataset Pruning
Laha Ale, Hu Luo, Mingsheng Cao et al. (+3 more)
Edge learning facilitates ubiquitous intelligence by enabling model training and adaptation directly on data-generating devices, thereby mitigating
privacy risks and communication latency. However, the high computational and energy overhead of on-device training hinders its deployment on battery-powered mobile systems with strict thermal and
memory budgets. While prior research has extensively optimized model architectures for efficient inference, the training phase remains bottlenecked by the processing of massive, often redundant, local
datasets. In this work, we propose a data-centric optimization framework that leverages
dataset pruning to achieve resource-efficient edge learning. Unlike standard methods that process all available data, our approach constructs compact, highly informative training subsets via a lightweight, on-device importance evaluation. Specifically, we utilize average loss statistics derived from a truncated warm-up phase to rank sample importance, deterministically retaining only the most critical data points under a dynamic
pruning ratio. This mechanism is model-agnostic and operates locally without inter-device communication. Extensive experiments on standard image classification
benchmarks demonstrate that our framework achieves a near-linear reduction in training latency and energy consumption proportional to the
pruning ratio, with negligible degradation in model accuracy. These results validate
dataset pruning as a vital, complementary paradigm for enhancing the sustainability and scalability of learning on resource-constrained mobile edge devices.
Read the full abstract ▾
All authors Laha Ale, Hu Luo, Mingsheng Cao, Shichao Li, Huanlai Xing, Haifeng Sun
Machine Learning
Extending Beacon to Hindi: Cultural Adaptation Drives Cross-Lingual Sycophancy
Sarthak Sattigeri
Sycophancy, the tendency of
language models to prioritize agreement with user preferences over principled
reasoning, has been identified as a persistent
alignment failure in English-
language evaluations. However, it remains unclear whether such diagnostics generalize across
languages and cultural contexts. We extend the Beacon single-turn forced-choice sycophancy diagnostic to Hindi through a controlled three-condition design: English original, Hindi literal translation, and Hindi culturally adapted
prompts. We evaluate four open-weight instruction-tuned models on 50
prompts per condition, enabling separation of
language encoding effects from cultural adaptation effects. Across all models, sycophancy rates are consistently higher for culturally adapted Hindi
prompts than for English, with absolute differences ranging from 12.0 to 16.0 percentage points. A decomposition on Qwen 2.5-Coder-7B shows that cultural adaptation (delta = 14.0%, 95% CI: [4.0%, 26.0%]) accounts for the majority of this gap, while
language encoding contributes minimally (delta = 2.0%, 95% CI: [0.0%, 6.0%]). Category-level analysis reveals that advice
prompts exhibit the largest cross-lingual differences (20-25 percentage points), achieving statistical significance in two of four models. These findings indicate that
alignment behaviors measured in English may not transfer uniformly across
languages and that culturally grounded
prompt framing plays a substantial role. We release all
datasets and evaluation code to support replication and extension.
Read the full abstract ▾
Machine Learning
Enhancing few-shot time series forecasting with LLM-guided diffusion
Haonan Shi, Dehua Shuai, Liming Wang et al. (+2 more)
Time series
forecasting in specialized domains is often constrained by limited data availability, where conventional models typically require large-scale
datasets to effectively capture underlying temporal dynamics. To tackle this few-shot challenge, we propose LTSM-DIFF (Large-scale Temporal Sequential
Memory with
Diffusion), a novel learning framework that integrates the expressive power of large
language models with the generative capability of
diffusion models. Specifically, the LTSM module is fine-tuned and employed as a temporal
memory mechanism, extracting rich sequential representations even under data-scarce conditions. These representations are then utilized as conditional guidance for a joint probability
diffusion process, enabling refined modeling of complex temporal patterns. This design allows knowledge transfer from the
language domain to time series tasks, substantially enhancing both generalization and robustness. Extensive experiments across diverse
benchmarks demonstrate that LTSM-DIFF consistently achieves state-of-the-art performance in data-rich scenarios, while also delivering significant improvements in few-shot
forecasting. Our work establishes a new paradigm for time series analysis under data scarcity.
Read the full abstract ▾
All authors Haonan Shi, Dehua Shuai, Liming Wang, Xiyang Liu, Long Tian
Machine Learning · Cross-listed from q-fin.ST
Bitcoin Price Prediction using Machine Learning and Combinatorial Fusion Analysis
Yuanhong Wu, Wei Ye, Jingyan Xu et al. (+1 more)
In this work, we propose to apply a new model fusion and learning paradigm, known as Combinatorial Fusion Analysis (CFA), to the field of Bitcoin price prediction. Price prediction of financial product has always been a big topic in finance, as the successful prediction of the price can yield significant profit. Every machine learning model has its own strength and weakness, which hinders progress toward robustness. CFA has been used to enhance models by leveraging rank-score characteristic (RSC) function and cognitive diversity in the combination of a moderate set of diverse and relatively well-performed models. Our method utilizes both score and rank combinations as well as other weighted combination techniques. Key metrics such as RMSE and MAPE are used to evaluate our methodology performance. Our proposal presents a notable MAPE performance of 0.19%. The proposed method greatly improves upon individual model performance, as well as outperforms other Bitcoin price prediction models.
Read the full abstract ▾
All authors Yuanhong Wu, Wei Ye, Jingyan Xu, D. Frank Hsu
Machine Learning · Cross-listed from cs.CL
In Vino Veritas and Vulnerabilities: Examining LLM Safety via Drunk Language Inducement
Anudeex Shetty, Aditya Joshi and Salil S. Kanhere
Humans are susceptible to undesirable behaviours and
privacy leaks under the influence of alcohol. This paper investigates drunk
language, i.e., text written under the influence of alcohol, as a driver for safety failures in large
language models (LLMs). We investigate three mechanisms for inducing drunk
language in LLMs: persona-based prompting, causal fine-tuning, and reinforcement-based post-training. When evaluated on 5 LLMs, we observe a higher susceptibility to jailbreaking on JailbreakBench (even in the presence of defences) and
privacy leaks on ConfAIde, where both
benchmarks are in English, as compared to the base LLMs as well as previously reported approaches. Via a robust combination of manual evaluation and LLM-based evaluators and analysis of error categories, our findings highlight a correspondence between human-intoxicated behaviour, and anthropomorphism in LLMs induced with drunk
language. The simplicity and efficiency of our drunk
language inducement approaches position them as potential counters for LLM safety tuning, highlighting significant risks to LLM safety.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.AP
Beyond Sustainable Development Goal (SDG) Accelerators: Directed Evidence for Adaptive Sustainability Portfolios
Md Muhtasim Munif Fahim, Md Jahid Hasan Imran, Md. Naim Molla et al. (+6 more)
Governments and development partners often seek Sustainable Development Goal (SDG) "accelerators" whose progress can propagate gains across human well-being, institutions, resources, and environmental priorities. Such claims require evidence on direction, timing, robustness, and trade-offs, not only network connectivity. We map directed SDG interdependence using a balanced panel of 114 countries observed annually from 2000 to 2024. Because the goal series are persistent, trending, and cross-sectionally dependent, we combine Dumitrescu-Hurlin panel Granger non-causality tests on first-differenced series with false-discovery control across 272 directed goal pairs, and panel local projections with Driscoll-Kraay standard errors for 31 theory-derived indicator linkages. We find 84 directed linkages after correction: 40 synergies and 44 trade-offs. This dense structure does not support a universal accelerator. Driver-receiver rankings are fragile across lag orders, centrality metrics, bootstrap resampling, and alternative dependence controls; only peace and strong institutions as a net receiver and poverty reduction as an effect-size-weighted driver are distinguishable in the bootstrap screen. Two local-projection pathways are supported, both leading to lower child mortality, and the education-child-health association is corroborated in independent World Development Indicators data across 183 countries. The policy implication is not to abandon SDG integration, but to replace fixed global accelerator rankings with adaptive portfolios built around supported, time-lagged linkages and monitored constituent indicators.
Read the full abstract ▾
All authors Md Muhtasim Munif Fahim, Md Jahid Hasan Imran, Md. Naim Molla, Luknath Debnath, Tonmoy Shil, Ehsanul Bashar Pranto, Md Mostafizur Rahman Likhon, Md Shafin Sanyan Saad, Md. Rezaul Karim
Machine Learning
Classifier Calibration at Scale: An Empirical Study of Model-Agnostic Post-Hoc Methods
Valery Manokhin and Daniel Grønhaug
We study model-agnostic post-hoc calibration methods intended to improve probabilistic predictions in supervised binary classification on real i.i.d. tabular data, with particular emphasis on conformal and Venn-based approaches that provide distribution-free validity guarantees under exchangeability. We
benchmark 21 widely used classifiers, including linear models, SVMs, tree ensembles (CatBoost, XGBoost, LightGBM), and modern tabular neural and foundation models, on binary tasks from the TabArena-v0.1 suite using randomized, stratified five-fold cross-validation with a held-out test fold. Five calibrators; Isotonic regression, Platt scaling, Beta calibration, Venn-Abers predictors, and Pearsonify are trained on a separate calibration split and applied to test predictions. Calibration is evaluated using proper scoring rules (log-loss and Brier score) and diagnostic measures (Spiegelhalter's Z, ECE, and ECI), alongside discrimination (AUC-ROC) and standard classification metrics. Across tasks and architectures, Venn-Abers predictors achieve the largest average reductions in log-loss, followed closely by Beta calibration, while Platt scaling exhibits weaker and less consistent effects. Beta calibration improves log-loss most frequently across tasks, whereas Venn-Abers displays fewer instances of extreme degradation and slightly more instances of extreme improvement. Importantly, we find that commonly used calibration procedures, most notably Platt scaling and isotonic regression, can systematically degrade proper scoring performance for strong modern tabular models. Overall classification performance is often preserved, but calibration effects vary substantially across
datasets and architectures, and no method dominates uniformly. In expectation, all methods except Pearsonify slightly increase accuracy, but the effect is marginal, with the largest expected gain about 0.008%.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Diagnosis Support of Sickle Cell Anemia by Classifying Red Blood Cell Shape in Peripheral Blood Images
Wilkie Delgado-Font, Miriela Escobedo-Nicot, Manuel González-Hidalgo et al. (+3 more)
Red blood
cell (RBC) deformation is the consequence of several diseases, including sickle
cell anemia, which causes recurring episodes of pain and severe pronounced anemia. Monitoring patients with these diseases involves the observation of peripheral blood samples under a microscope, a time-consuming procedure. Moreover, a specialist is required to perform this technique, and owing to the subjective nature of the observation of isolated RBCs, the error rate is high. In this paper, we propose an automated method for differentially enumerating RBCs that uses peripheral blood smear image analysis. In this method, the objects of interest in the image are segmented using a Chan-Vese active contour model. An analysis is then performed to classify the RBCs, also called erythrocytes, as normal or elongated or having other deformations, using the basic shape analysis descriptors: circular shape factor (CSF) and elliptical shape factor (ESF). To analyze
cells that become partially occluded in a cluster during sample preparation, an elliptical adjustment is performed to allow the analysis of erythrocytes with discoidal and elongated shapes. The images of patient blood samples used in the study were acquired by a clinical laboratory specialist in the Special Hematology Department of the “Dr. Juan Bruno Zayas” General Hospital in Santiago de Cuba. A comparison of the results obtained by the proposed method in our experiments with those obtained by some state-of-the-art methods showed that the proposed method is superior for the diagnosis of sickle
cell anemia. This superiority is achieved for evidenced by the obtained F-measure value (0.97 for normal
cells and 0.95 for elongated ones) and several overall multiclass performance measures. The results achieved by the proposed method are suitable for the purpose of clinical treatment and diagnostic support of sickle
cell anemia.
Read the full abstract ▾
All authors Wilkie Delgado-Font, Miriela Escobedo-Nicot, Manuel González-Hidalgo, Silena Herold-Garcia, Antoni Jaume-i-Capó, Arnau Mir
Machine Learning · Cross-listed from cs.CR
Tracing the Data Trail: A Survey of Data Provenance, Transparency and Traceability in LLMs
Richard Hohensinner, Belgin Mutlu, Inti Gabriel Mendoza Estrada et al. (+3 more)
Large
language models (LLMs) are deployed at scale, yet their training data life cycle remains opaque. This survey synthesizes research from the past ten years on three tightly coupled axes: (1) data provenance, (2) transparency, and (3) traceability, and three supporting pillars: (4) bias & uncertainty, (5) data
privacy, and (6) tools and techniques that operationalize them. A central contribution is a proposed taxonomy defining the field's domains and listing corresponding artifacts. Through analysis of 95 publications, this work identifies key methodologies concerning data generation, watermarking, bias measurement, data curation, data
privacy, and the inherent trade-off between transparency and opacity.
Read the full abstract ▾
All authors Richard Hohensinner, Belgin Mutlu, Inti Gabriel Mendoza Estrada, Matej Vukovic, Simone Kopeinik, Roman Kern
Machine Learning · Cross-listed from cs.AI
Graph Neural Networks are Heuristics
Yimeng Min and Carla P. Gomes
Graph neural networks are usually treated as auxiliaries for combinatorial optimization: they imitate
algorithms, guide search, or supply scores to classical procedures. We show that this auxiliary role is not intrinsic. A GNN can itself be a heuristic. For the Euclidean Travelling Salesman Problem, we train a non-autoregressive GNN with no labels, rewards, sequential decoding, search, or local improvement. A differentiable
Hamiltonian-cycle objective is the only supervision. The trained model produces a complete tour in one forward pass, while dropout and snapshots from a single training trajectory provide solution diversity without engineered moves. The heuristic is therefore learned, not programmed. It is also fast: batched inference remains in the millisecond regime on GPUs. Experiments on TSP100, TSP200, and TSP500 show that the model consistently improves over nearest-neighbor greedy baselines. These results identify unsupervised GNNs as a class of fast learned heuristics for combinatorial optimization.
Read the full abstract ▾
Machine Learning
Quantum Qualifiers for Neural Network Model Selection in Hadronic Physics
Brandon B. Le and D. Keller
As
quantum machine-learning architectures mature, a central challenge is no longer their construction, but identifying the regimes in which they offer practical advantages over classical approaches. In this work, we introduce a framework for addressing this question in data-driven hadronic physics problems by developing diagnostic tools - centered on a quantitative
quantum qualifier - that guide model selection between classical and
quantum deep neural networks based on intrinsic properties of the data. Using controlled classification and regression studies, we show how relative model performance follows systematic trends in complexity, noise, and dimensionality, and how these trends can be distilled into a predictive criterion. We then demonstrate the utility of this approach through an application to Compton form factor extraction from deeply virtual Compton scattering, where the
quantum qualifier identifies kinematic regimes favorable to
quantum models. Together, these results establish a principled framework for deploying
quantum machine-learning tools in precision hadronic physics.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Labels or Preferences? Budget-Constrained Learning with Human Judgments over AI-Generated Outputs
Zihan Dong, Xiaotian Hou, Ruijia Wu et al. (+1 more)
The increasing reliance on human preference feedback to judge AI-generated pseudo labels has created a pressing need for principled, budget-conscious data acquisition strategies. We address the crucial question of how to optimally allocate a fixed annotation budget between ground-truth labels and pairwise preferences in AI. Our solution, grounded in semi-parametric inference, casts the budget allocation problem as a monotone missing data framework. Building on this formulation, we introduce Preference-Calibrated Active Learning (PCAL), a novel method that learns the optimal data acquisition strategy and develops a statistically efficient
estimator for functionals of the data distribution. Theoretically, we prove the asymptotic optimality of our PCAL
estimator and establish a key robustness guarantee that ensures robust performance even with poorly estimated nuisance models. Our flexible framework applies to a general class of problems, by directly optimizing the
estimator's variance instead of requiring a closed-form solution. This work provides a principled and statistically efficient approach for budget-constrained learning in modern AI. Simulations and real-data analysis demonstrate the practical benefits and superior performance of our proposed method.
Read the full abstract ▾
All authors Zihan Dong, Xiaotian Hou, Ruijia Wu, Linjun Zhang
Machine Learning
Federated Learning Under Temporal Drift – Mitigating Catastrophic Forgetting via Experience Replay
Sahasra Kokkula, Daniel David and Aaditya Baruah
Federated Learning struggles under temporal concept drift where client data distributions shift over time. We demonstrate that standard FedAvg suffers catastrophic forgetting under seasonal drift on Fashion-MNIST, with accuracy dropping from 74% to 28%. We propose client-side experience replay, where each client maintains a small buffer of past samples mixed with current data during local training. This simple approach requires no changes to server aggregation. Experiments show that a 50-sample-per-class buffer restores performance to 78-82%, effectively preventing forgetting. Our ablation study reveals a clear
memory-accuracy trade-off as buffer size increases.
Read the full abstract ▾