Machine Learning · Cross-listed from cs.AI
Explaining AI Without Code: A User Study on Explainable AI
Natalia Abarca, Andrés Carvallo, Claudia López Moncada et al. (+1 more)
The increasing use of Machine Learning (ML) in sensitive domains such as healthcare, finance, and public policy has raised concerns about the transparency of automated decisions. Explainable AI (XAI) addresses this by clarifying how models generate predictions, yet most methods demand technical expertise, limiting their value for novices. This gap is especially critical in no-code ML platforms, which seek to democratize AI but rarely include explainability. We present a human-centered XAI module in DashAI, an open-source no-code ML platform. The module integrates three complementary techniques, which are Partial Dependence Plots (PDP), Permutation Feature Importance (PFI), and KernelSHAP, into DashAI's workflow for tabular classification. A user study (N = 20; ML novices and experts) evaluated usability and the impact of explanations. Results show: (i) high task success ($\geq80\%$) across all explainability tasks; (ii) novices rated explanations as useful, accurate, and trustworthy on the Explanation Satisfaction Scale (ESS, Cronbach's $\alpha$ = 0.74, a measure of internal consistency), while experts were more critical of sufficiency and completeness; and (iii) explanations improved perceived predictability and confidence on the Trust in Automation scale (TiA, $\alpha$ = 0.60), with novices showing higher trust than experts. These findings highlight a central challenge for XAI in no-code ML, making explanations both accessible to novices and sufficiently detailed for experts.
Read the full abstract ▾
All authors Natalia Abarca, Andrés Carvallo, Claudia López Moncada, Felipe Bravo-Marquez
Machine Learning · Cross-listed from cs.CL
SciNets: Graph-Constrained Multi-Hop Reasoning for Scientific Literature Synthesis
Sauhard Dubey
Cross-domain scientific synthesis requires connecting mechanistic explanations across fragmented literature, a capability that remains challenging for both
retrieval-based systems and unconstrained
language models. While recent work has applied large
language models to scientific summarization and question answering, these approaches provide limited control over
reasoning depth and structural grounding. We frame mechanistic synthesis as a graph-constrained multi-hop
reasoning problem over literature-derived concept graphs. Given a scientific query and a compact, query-local corpus, SciNets constructs a directed concept graph and synthesizes mechanistic explanations by identifying multi-hop
reasoning paths that connect concepts that rarely co-occur within individual papers. We systematically compare shortest-path
reasoning, k-shortest paths with diversity constraints,
stochastic random walks, and a
retrieval-augmented
language model baseline. Rather than evaluating correctness, which is often indeterminate when synthesizing connections across distributed sources, we introduce a behavioral framework that measures symbolic
reasoning depth, mechanistic diversity, and grounding stability. Across machine learning, biology, and
climate science tasks, explicit graph constraints enable controllable multi-hop
reasoning while revealing a consistent trade-off: deeper and more diverse symbolic
reasoning increases grounding instability, whereas shortest-path
reasoning remains highly stable but structurally conservative. These findings provide a systematic behavioral characterization of the limits and capabilities of current graph-LLM integration for scientific synthesis.
Read the full abstract ▾
Machine Learning
Enabling Long FFT Convolutions on Memory-Constrained FPGAs via Chunking
Peter Wang, Neelesh Gupta and Viktor Prasanna
The need for long-context
reasoning has led to alternative neural network architectures besides
Transformers and self-
attention, a popular model being Hyena, which employs causal 1D-convolutions implemented with FFTs. Long convolutions enable efficient global context mixing, but requirements for intermediate results exceed the 2-3 MB Block RAM capacity of FPGAs. We present a chunked FFT convolution approach enabling 450K length sequence by 450K length filter convolutions on an Alveo U200 FPGA with 2.8 MB BRAM through chunking and overlap-add reconstruction. We find that throughput scales proportionally with chunk size while degrading minimally by 7% for our longest sequences, demonstrating that careful
memory management enables deployment of long-context primitives on edge FPGAs without sacrificing performance.
Read the full abstract ▾
Machine Learning · Cross-listed from eess.SP
Channel Selected Stratified Nested Cross Validation for Clinically Relevant EEG Based Parkinsons Disease Detection
Nicholas R. Rasmussen, Rodrigue Rizk, Longwei Wang et al. (+2 more)
The early detection of Parkinsons disease remains a critical challenge in clinical neuroscience, with electroencephalography offering a noninvasive and scalable pathway toward population level screening. While machine learning has shown promise in this domain, many reported results suffer from methodological flaws, most notably patient level data leakage, inflating performance estimates and limiting clinical translation. To address these modeling pitfalls, we propose a unified evaluation framework grounded in nested cross validation and incorporating three complementary safeguards: (i) patient level stratification to eliminate subject overlap and ensure unbiased generalization, (ii) multi layered windowing to harmonize heterogeneous
EEG recordings while preserving temporal dynamics, and (iii) inner loop channel selection to enable principled feature reduction without information leakage. Applied across three independent
datasets with a heterogeneous number of channels, a convolutional neural network trained under this framework achieved 80.6% accuracy and demonstrated state of the art performance under held out population block testing, comparable to other methods in the literature. This performance underscores the necessity of nested cross validation as a safeguard against bias and as a principled means of selecting the most relevant information for patient level decisions, providing a reproducible foundation that can extend to other biomedical signal analysis domains.
Read the full abstract ▾
All authors Nicholas R. Rasmussen, Rodrigue Rizk, Longwei Wang, Arun Singh, KC Santosh
Machine Learning · Cross-listed from q-fin.ST
On the use of case estimate and transactional payment data in neural networks for individual loss reserving
Benjamin Avanzi, Matthew Lambrianidis, Greg Taylor et al. (+1 more)
The use of neural networks trained on individual claims data has become increasingly popular in the actuarial reserving literature. We consider how to best input historical payment data in neural network models. Additionally, case estimates are also available in the format of a time series, and we extend our analysis to assessing their predictive power. In this paper, we compare a feed-forward neural network trained on summarised transactions to a recurrent neural network equipped to analyse a claim's entire payment history and/or case estimate development history. We draw conclusions from training and comparing the performance of the models on multiple, comparable highly complex
datasets simulated from SPLICE (Avanzi, Taylor and Wang, 2023). In environments where
covariate data is limited, we find evidence that case estimates will improve predictions substantially, but that equipping the neural network with
memory only leads to meagre improvements. Although the case estimation process and quality will vary significantly between insurers, we provide a standardised methodology for assessing their value.
Read the full abstract ▾
All authors Benjamin Avanzi, Matthew Lambrianidis, Greg Taylor, Bernard Wong
Machine Learning · Cross-listed from q-bio.OT
MixRx: Predicting Drug Combination Interactions with LLMs
Risha Surana, Cameron Saidock and Hugo Chacon
MixRx uses Large
Language Models (LLMs) to classify drug combination interactions as Additive, Synergistic, or Antagonistic, given a multi-drug patient history. We evaluate the performance of 4 models, GPT-2, Mistral Instruct 2.0, and the fine-tuned counterparts. Our results showed a potential for such an application, with the Mistral Instruct 2.0 Fine-Tuned model providing an average accuracy score on standard and perturbed
datasets of 81.5%. This paper aims to further develop an upcoming area of research that evaluates if LLMs can be used for biological prediction tasks.
Read the full abstract ▾
Machine Learning
Value-guided action planning with JEPA world models
Matthieu Destrade, Oumayma Bounou, Quentin Le Lidec et al. (+2 more)
Building deep learning models that can reason about their environment requires capturing its underlying dynamics. Joint-Embedded Predictive Architectures (JEPA) provide a promising framework to model such dynamics by learning representations and predictors through a self-supervised prediction objective. However, their ability to support effective action planning remains limited. We propose an approach to enhance planning with JEPA world models by shaping their representation space so that the negative goal-conditioned value function for a reaching cost in a given environment is approximated by a distance (or quasi-distance) between state
embeddings. We introduce a practical method to enforce this constraint during training and show that it leads to significantly improved planning performance compared to standard JEPA models on simple control tasks.
Read the full abstract ▾
All authors Matthieu Destrade, Oumayma Bounou, Quentin Le Lidec, Jean Ponce, Yann LeCun
Machine Learning
Neural Optimal Design of Experiment for Inverse Problems
John E. Darges, Babak Maboudi Afkham and Matthias Chung
We introduce Neural Optimal Design of Experiments, a learning-based framework for optimal experimental design in inverse problems that avoids classical bilevel optimization and indirect sparsity regularization. NODE jointly trains a neural reconstruction model and a fixed-budget set of continuous design variables representing sensor locations, sampling times, or measurement angles, within a single optimization loop. By optimizing measurement locations directly rather than weighting a dense grid of candidates, the proposed approach enforces sparsity by design, eliminates the need for l1 tuning, and substantially reduces computational complexity. We validate NODE on an analytically tractable exponential growth
benchmark, on MNIST image sampling, and illustrate its effectiveness on a real world sparse view X ray CT example. In all cases, NODE outperforms baseline approaches, demonstrating improved reconstruction accuracy and task-specific performance.
Read the full abstract ▾
Machine Learning
Dominik Soukup, Richard Plný, Daniel Vašata et al. (+1 more)
Machine learning (ML) represents an efficient and popular approach for network traffic classification. However, network traffic classification is a challenging domain, and trained models may degrade soon after deployment due to the obsolete
datasets and quick
evolution of computer networks as new or updated protocols appear. Moreover, significant change in the behavior of a traffic type (and, therefore, the underlying features representing the traffic) can produce a large and sudden performance drop of the deployed model, known as a data or concept drift. In most cases, complete retraining is performed, often without further investigation of root causes, as good
dataset quality is assumed. However, this is not always the case and further investigation must be performed. This paper proposes a novel methodology to evaluate the stability of
datasets and a
benchmark workflow that can be used to compare
datasets. The proposed framework is based on a concept drift detection method that also uses ML feature weights to boost the detection performance. The benefits of this work are demonstrated on CESNET-TLS-Year22
dataset. We provide the initial
dataset stability
benchmark that is used to describe
dataset stability and weak points to identify the next steps for optimization. Lastly, using the proposed benchmarking methodology, we show the optimization impact on the created
dataset variants.
Read the full abstract ▾
All authors Dominik Soukup, Richard Plný, Daniel Vašata, Tomáš Čejka
Machine Learning
Learning Coupled System Dynamics under Incomplete Physical Constraints and Missing Data
Esha Saha and Hao Wang
Advances in data acquisition and computational methods have accelerated the use of differential equation based modelling for complex systems. Such systems are often described by coupled (or more) variables, yet governing equation is typically available for one variable, while the remaining variable can be accessed only through data. This mismatch between known physics and observed data poses a fundamental challenge for existing physics-informed machine learning approaches, which generally assume either complete knowledge of the governing equations or full data availability across all variables. In this paper, we introduce MUSIC (Multitask Learning Under Sparse and Incomplete Constraints), a sparsity induced multitask neural network framework that integrates partial physical constraints with data-driven learning to recover full-dimensional solutions of coupled systems when physics-constrained and data-informed variables are mutually exclusive. MUSIC employs mesh-free (random) sampling of training data and sparsity regularization, yielding highly compressed models with improved training and evaluation efficiency. We demonstrate that MUSIC accurately learns solutions (shock wave solutions, discontinuous solutions, pattern formation solutions) to complex coupled systems under data-scarce and noisy conditions, consistently outperforming non-sparse formulations. These results highlight MUSIC as a flexible and effective approach for modeling partially observed systems with incomplete physical knowledge.
Read the full abstract ▾
Machine Learning
How Much Data Is Enough? Uniform Convergence Bounds for Generative & Vision-Language Models under Low-Dimensional Structure
Paul M. Thompson
Modern generative and
vision-
language models (VLMs) are increasingly used in scientific and medical decision support, where predicted probabilities must be both accurate and well calibrated. Despite strong empirical results with moderate data, it remains unclear when such predictions generalize uniformly across inputs, classes, or subpopulations, rather than only on average-a critical issue in biomedicine, where rare conditions and specific groups can exhibit large errors even when overall loss is low. We study this question from a finite-sample perspective and ask: under what structural assumptions can generative and VLM-based predictors achieve uniformly accurate and calibrated behavior with practical sample sizes? Rather than analyzing arbitrary parameterizations, we focus on induced families of classifiers obtained by varying
prompts or semantic
embeddings within a restricted representation space. When model outputs depend smoothly on a low-dimensional semantic representation-an assumption supported by spectral structure in text and joint image-text
embeddings-classical uniform convergence tools yield meaningful non-asymptotic guarantees. Our main results give finite-sample uniform convergence bounds for accuracy and calibration functionals of VLM-induced classifiers under Lipschitz stability with respect to
prompt embeddings. The implied sample complexity depends on intrinsic/effective dimension, not ambient
embedding dimension, and we further derive spectrum-dependent bounds that make explicit how
eigenvalue decay governs data requirements. We conclude with implications for data-limited biomedical modeling, including when current
dataset sizes can support uniformly reliable predictions and why average calibration metrics may miss worst-case miscalibration.
Read the full abstract ▾
Machine Learning
A Note on Hybrid Online Reinforcement and Imitation Learning for LLMs: Formulations and Algorithms
Yingru Li, Ziniu Li and Jiacai Liu
We present a unified framework for Large
Language Model (LLM) fine-tuning that integrates Imitation Learning and Reinforcement Learning. By analyzing the gradient of a composite objective combining trajectory-level KL divergence with task rewards, we derive a natural decomposition into two components: (1) an analytically computable Dense Gradient for
token-level imitation, and (2) a Monte Carlo estimated Sparse Gradient for long-horizon reward optimization. The Dense Gradient admits a closed-form logit-level formula, enabling efficient GPU implementation.
Read the full abstract ▾
Machine Learning
Osmotic Learning: A Self-Supervised Paradigm for Decentralized Contextual Data Representation
Mario Colosi, Reza Farahani, Maria Fazio et al. (+2 more)
Data within a specific context gains deeper significance beyond its isolated interpretation. In distributed systems, interdependent data sources reveal hidden relationships and latent structures, representing valuable information for many applications. This paper introduces Osmotic Learning (OSM-L), a self-supervised distributed learning paradigm designed to uncover higher-level latent knowledge from distributed data. The core of OSM-L is osmosis, a process that synthesizes dense and compact representation by extracting contextual information, eliminating the need for raw data exchange between distributed entities. OSM-L iteratively aligns local data representations, enabling information
diffusion and convergence into a dynamic
equilibrium that captures contextual patterns. During training, it also identifies correlated data groups, functioning as a decentralized clustering mechanism. Experimental results confirm OSM-L's convergence and representation capabilities on structured
datasets, achieving over 0.99 accuracy in local information
alignment while preserving contextual integrity.
Read the full abstract ▾
All authors Mario Colosi, Reza Farahani, Maria Fazio, Radu Prodan, Massimo Villari
Machine Learning · Cross-listed from cs.AI
Benchmark Success, Clinical Failure: When Reinforcement Learning Optimizes for Benchmarks, Not Patients
Armin Berger, Manuela Bergau, Helen Schneider et al. (+7 more)
Recent Reinforcement Learning (RL) advances for Large
Language Models (LLMs) have improved
reasoning tasks, yet their resource-constrained application to medical imaging remains underexplored. We introduce ChexReason, a
vision-
language model trained via R1-style methodology (SFT followed by GRPO) using only 2,000 SFT samples, 1,000 RL samples, and a single A100 GPU. Evaluations on CheXpert and NIH
benchmarks reveal a fundamental tension: GRPO recovers in-distribution performance (23% improvement on CheXpert, macro-F1 = 0.346) but degrades cross-
dataset transferability (19% drop on NIH). This mirrors high-resource models like NV-Reason-CXR-3B, suggesting the issue stems from the RL paradigm rather than scale. We identify a generalization paradox where the SFT checkpoint uniquely improves on NIH before optimization, indicating teacher-guided
reasoning captures more institution-agnostic features. Furthermore, cross-model comparisons show structured
reasoning scaffolds benefit general-purpose VLMs but offer minimal gain for medically pre-trained models. Consequently, curated supervised fine-tuning may outperform aggressive RL for clinical deployment requiring robustness across diverse populations.
Read the full abstract ▾
All authors Armin Berger, Manuela Bergau, Helen Schneider, Saad Ahmad, Tom Anglim Lagones, Gianluca Brugnara, Martha Foltyn-Dumitru, Kai Schlamp, Philipp Vollmuth, Rafet Sifa
Machine Learning
Dynamic Vocabulary Pruning: Stable LLM-RL by Taming the Tail
Yingru Li, Jiawei Xu, Jiacai Liu et al. (+6 more)
Reinforcement Learning (RL) for Large
Language Models (LLMs) faces a fundamental tension: the numerical divergence between high-throughput inference engines and numerically precise training engines. Although these systems share the same parameters, they produce slightly different probability distributions, creating a training-inference mismatch. We prove that the bound on the log-probability divergence arising from this mismatch scales as $(1-p)$, where $p$ is the
token probability. This scaling induces a highly asymmetric effect: the bound vanishes for high-probability
tokens but remains significant for low-probability
tokens in the distribution tail. When sampled, these tail
tokens introduce systematically biased errors that accumulate over sequences, thereby destabilizing gradient estimation. Instead of applying post-hoc corrections, we propose Dynamic Vocabulary
Pruning (DVP), which constrains the RL objective to a dynamically determined ”safe” vocabulary that excludes the extreme tail. This strategy trades large, destabilizing numerical errors for a small, bounded optimization bias. We validate DVP empirically by demonstrating stable training, and theoretically by deriving strict bounds on the induced bias.
Read the full abstract ▾
All authors Yingru Li, Jiawei Xu, Jiacai Liu, Yuxuan Tong, Ziniu Li, Tianle Cai, Ge Zhang, Qian Liu, Baoxiang Wang
Machine Learning · Cross-listed from physics.chem-ph
QSAR-Guided Generative Framework for the Discovery of Synthetically Viable Odorants
Tim C. Pearce and Ahmed Ibrahim
The discovery of novel odorant molecules is key for the fragrance and
flavor industries, yet efficiently navigating the vast chemical space to identify structures with desirable olfactory properties remains a significant challenge. Generative artificial intelligence offers a promising approach for de novo molecular design but typically requires large sets of molecules to learn from. To address this problem, we present a framework combining a variational autoencoder (VAE) with a quantitative structure-activity relationship (QSAR) model to generate novel odorants from limited training sets of odor molecules. The self-supervised learning capabilities of the VAE allow it to learn SMILES grammar from ChEMBL database, while its training objective is augmented with a loss term derived from an external QSAR model to structure the latent representation according to odor probability. While the VAE demonstrated high internal consistency in learning the QSAR supervision signal, validation against an external, unseen ground truth
dataset (Unique Good Scents) confirms the model generates syntactically valid structures (100% validity achieved via rejection sampling) and 93.9% unique structures. The latent space is effectively structured by odor likelihood, evidenced by a Frechet ChemNet Distance (FCD) of ~6.96 between generated molecules and known odorants, compared to ~21.6 for the ChEMBL baseline. An ablation of the property head shows that its contribution lies in the density of retrievable structures near an odorant seed – a 4.3-fold increase in distinct novel compounds per seed – rather than in the odor-likeness of any individual compound. Bemis-Murcko analysis shows 2,499 of 6,765 ring-containing candidates, spanning 1,429 distinct core frameworks, absent from all training sets, while a further 294 molecules...
Read the full abstract ▾
Machine Learning · Cross-listed from q-fin.GN
Deep Learning for Art Market Valuation
Jianping Mei, Michael Moses, Jan Waelty et al. (+1 more)
We study how deep learning can improve valuation in the art
market by incorporating the visual content of artworks into predictive models. Using a large repeated-sales
dataset from major auction houses, we
benchmark classical hedonic regressions and tree-based methods against modern deep architectures, including multi-modal models that fuse tabular and image data. We find that while artist identity and prior transaction history dominate overall predictive power, visual
embeddings provide a distinct and economically meaningful contribution for fresh-to-
market works where historical anchors are absent. Interpretability analyses using Grad-CAM and
embedding visualizations show that models attend to compositional and stylistic cues. Our findings demonstrate that multi-modal deep learning delivers significant value precisely when valuation is hardest, namely first-time sales, and thus offers new insights for both academic research and practice in art
market valuation.
Read the full abstract ▾
All authors Jianping Mei, Michael Moses, Jan Waelty, Yucheng Yang
Machine Learning
Multimodal Functional Maximum Correlation for Emotion Recognition
Deyang Zheng, Tianyi Zhang, Wenming Zheng et al. (+1 more)
Emotional states manifest as coordinated yet heterogeneous physiological responses across central and autonomic systems, posing a fundamental challenge for
multimodal representation learning in affective computing. Learning such joint dynamics is further complicated by the scarcity and subjectivity of affective annotations, which motivates the use of self-supervised learning (SSL). However, most existing SSL approaches rely on pairwise
alignment objectives, which are insufficient to characterize dependencies among more than two modalities and fail to capture higher-order interactions arising from coordinated
brain and autonomic responses. To address this limitation, we propose
Multimodal Functional Maximum Correlation (MFMC), a principled SSL framework that maximizes higher-order
multimodal dependence through a Dual Total Correlation (DTC) objective. By deriving a tight sandwich bound and optimizing it using a functional maximum correlation analysis (FMCA) based trace surrogate, MFMC captures joint
multimodal interactions directly, without relying on pairwise contrastive losses. Experiments on three public affective computing
benchmarks demonstrate that MFMC consistently achieves state-of-the-art or competitive performance under both subject-dependent and subject-independent evaluation protocols, highlighting its robustness to inter-subject variability. In particular, MFMC improves subject-dependent accuracy on CEAP-360VR from 78.9% to 86.8%, and subject-independent accuracy from 27.5% to 33.1% using the EDA signal alone. Moreover, MFMC remains within 0.8 percentage points of the best-performing method on the most challenging
EEG subject-independent split of MAHNOB-HCI. Our code is available at https://github.com/DY9910/MFMC.
Read the full abstract ▾
All authors Deyang Zheng, Tianyi Zhang, Wenming Zheng, Shujian Yu
Machine Learning
Trust Region Masking for Long-Horizon LLM Reinforcement Learning
Yingru Li, Jiacai Liu, Jiawei Xu et al. (+4 more)
Policy gradient methods for Large
Language Models optimize a policy $\pi_\theta$ via a surrogate objective computed from samples of a rollout policy $\pi_{\text{roll}}$. However, modern LLM-RL pipelines suffer from unavoidable implementation divergences – backend discrepancies, Mixture-of-Experts routing discontinuities, and distributed training staleness – causing off-policy mismatch ($\pi_{\text{roll}} \neq \pi_\theta$) and approximation errors between the surrogate and the true objective. We demonstrate that classical trust region bounds on this error scale as $O(T^2)$ with sequence length $T$, rendering them vacuous for long-horizon tasks. To address this, we derive a family of bounds – both KL-based and TV-based – including a Pinsker-Marginal bound ($O(T^{3/2})$), a Mixed bound ($O(T)$), and an Adaptive bound that strictly generalizes the Pinsker-Marginal bound via per-position importance-ratio decomposition. Taking the minimum over all bounds yields the tightest known guarantee across all divergence regimes. Crucially, all bounds depend on the maximum
token-level divergence $D_{\mathrm{KL}}^{\mathrm{tok,max}}$ (or $D_{\mathrm{TV}}^{\mathrm{tok,max}}$), a sequence-level quantity that cannot be controlled by
token-independent methods like PPO clipping. We propose Trust Region Masking (TRM), which masks entire sequences violating the trust region, enabling the first non-vacuous monotonic improvement guarantees for long-horizon LLM-RL.
Read the full abstract ▾
All authors Yingru Li, Jiacai Liu, Jiawei Xu, Yuxuan Tong, Ziniu Li, Qian Liu, Baoxiang Wang
Machine Learning
Rethinking Fine-Tuning: Unlocking Hidden Capabilities in Vision-Language Models
Mingyuan Zhang, Yue Bai, Yifan Wang et al. (+2 more)
Fine-tuning has become the dominant paradigm for adapting
Vision-
Language Models (VLMs), yet most approaches rely on explicit weight updates that introduce a fundamental trade-off. Full Fine-Tuning (FFT) may perturb pretrained representations due to cross-modal gradient interference, whereas Parameter-Efficient Fine-Tuning (PEFT) methods rely on additive modules, such as low-rank adapters, which may limit adaptation capacity. In this paper, we rethink VLM adaptation from a structural selection framework that adapts VLMs without modifying backbone weights, and we propose Mask Fine-Tuning (MFT). MFT learns masks that selectively route information through existing pretrained connections, dynamically uncovering subnetworks that better align pretrained representations with downstream objectives. Extensive experiments show that MFT provides an effective structural alternative to both FFT and PEFT, consistently achieving superior performance across multiple
vision-
language benchmarks without adding knowledge or altering the deployment architecture. Moreover, our analysis with MFT provides new insights into how pretrained VLMs reorganize their internal representational pathways during adaptation.
Read the full abstract ▾
All authors Mingyuan Zhang, Yue Bai, Yifan Wang, Yiyang Huang, Yun Fu
Machine Learning · Cross-listed from stat.ML
Federated Learning With L0 Constraint Via Probabilistic Gates For Sparsity
Krishna Harsha Kovelakuntla Huthasana, Alireza Olama and Andreas Lundell
Federated Learning (FL) is a distributed machine learning setting that requires multiple clients to collaborate on training a model while maintaining data
privacy. The unaddressed inherent sparsity in data and models often results in overly dense models and poor generalizability under data and client participation heterogeneity. We propose FL with an L0 constraint on the density of non-zero parameters, achieved through a reparameterization using probabilistic gates and their continuous relaxation: originally proposed for sparsity in centralized machine learning. We show that the objective for L0 constrained
stochastic minimization naturally arises from an
entropy maximization problem of the
stochastic gates and propose an
algorithm based on
federated stochastic gradient descent for distributed learning. We demonstrate that the target density (rho) of parameters can be achieved in FL, under data and client participation heterogeneity, with minimal loss in statistical performance for linear and non-linear models: Linear regression (LR), Logistic regression (LG), Softmax multi-class classification (MC), Multi-label classification with logistic units (MLC), Convolution Neural Network (CNN) for multi-class classification (MC). We compare the results with a magnitude
pruning-based thresholding
algorithm for sparsity in FL. Experiments on synthetic data with target density down to rho = 0.05 and publicly available RCV1, MNIST, and EMNIST
datasets with target density down to rho = 0.005 demonstrate that our approach is communication-efficient and consistently better in statistical performance.
Read the full abstract ▾
Machine Learning
FLEX-MoE: Federated Mixture-of-Experts with Load-balanced Expert Assignment for Edge Computing
Boyang Zhang, Xiaobing Chen, Songyang Zhang et al. (+4 more)
Mixture-of-Experts (MoE) models enable scalable neural networks through conditional computation, offering enhanced effectiveness and efficiency for next-generation wireless communications. However, deploying MoE with
federated learning (FL) over wireless and IoT edge networks faces two critical challenges: 1) resource-constrained clients cannot store large AI models with full expert sets, and 2) non-IID data distributions cause severe expert load imbalance that degrades model performance. To this end, we propose FLEX-MoE, a
federated MoE framework that jointly optimizes expert assignment and load balancing under limited client capacity. Specifically, our approach introduces client-expert fitness scores that quantify expert suitability for local
datasets through training feedback, and employs an optimization-based
algorithm to maximize client-expert specialization while enforcing balanced expert utilization system-wide. Unlike greedy methods that focus solely on personalization while ignoring load imbalance, FLEX-MoE addresses expert utilization skew, which is particularly severe in heterogeneous edge FL. Our experimental results demonstrate superior accuracy and consistently balanced expert utilization across diverse resource-constrained scenarios for edge computing.
Read the full abstract ▾
All authors Boyang Zhang, Xiaobing Chen, Songyang Zhang, Shuai Zhang, Xiangwei Zhou, Jian Zhang, Mingxuan Sun