Advances in neural information processing systems最新文献

{"title":"JADE: Joint Alignment and Deep Embedding for Multi-Slice Spatial Transcriptomics.","authors":"Yuanchuan Guo, Jun S Liu, Huimin Cheng, Ying Ma","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>As spatially resolved transcriptomics (SRT) datasets increasingly span multiple adjacent or replicated slices, effective joint analysis across slices is needed to reconstruct tissue structures and identify consistent spatial gene expression patterns. This requires resolving spatial correspondences between slices while capturing shared transcriptomic features, two tasks that are typically addressed in isolation. Multi-slice analysis remains challenging due to physical distortions, technical variability, and batch effects. To address these challenges, we introduce Joint Alignment and Deep Embedding for multi-slice SRT (JADE), a unified computational framework that simultaneously learns spatial location-wise alignments and shared low-dimensional embeddings across tissue slices. Unlike existing methods, JADE adopts a roundtrip framework in which each iteration alternates between alignment and embedding refinement. To infer alignment, we employ attention mechanisms that dynamically assess and weight the importance of different embedding dimensions, allowing the model to focus on the most alignment-relevant features while suppressing noise. To the best of our knowledge, JADE is the first method that jointly optimizes alignment and representation learning in a shared latent space, enabling robust multi-slice integration. We demonstrate that JADE outperforms existing alignment and embedding methods across multiple evaluation metrics in the 10x Visium human dorsolateral prefrontal cortex (DLPFC) and Stereo-seq axolotl brain datasets. By bridging spatial alignment and feature integration, JADE provides a scalable and accurate solution for cross-slice analysis of SRT data.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"25715-25748"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13281739/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148297418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Rich and the Simple: On the Implicit Bias of Adam and SGD.","authors":"Bhavya Vasudeva, Jung Whan Lee, Vatsal Sharan, Mahdi Soltanolkotabi","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Adam is the de facto optimization algorithm for several deep learning applications, but an understanding of its implicit bias and how it differs from other algorithms, particularly standard first-order methods such as (stochastic) gradient descent (GD), remains limited. In practice, neural networks (NNs) trained with SGD are known to exhibit simplicity bias - a tendency to find simple solutions. In contrast, we show that Adam is more resistant to such simplicity bias. First, we investigate the differences in the implicit biases of Adam and GD when training two-layer ReLU NNs on a binary classification task with Gaussian data. We find that GD exhibits a simplicity bias, resulting in a linear decision boundary with a suboptimal margin, whereas Adam leads to much richer and more diverse features, producing a nonlinear boundary that is closer to the Bayes' optimal predictor. This richer decision boundary also allows Adam to achieve higher test accuracy both in-distribution and under certain distribution shifts. We theoretically prove these results by analyzing the population gradients. Next, to corroborate our theoretical findings, we present extensive empirical results showing that this property of Adam leads to superior generalization across various datasets with spurious correlations where NNs trained with SGD are known to show simplicity bias and do not generalize well under certain distributional shifts.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"161725-161761"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13225676/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148152348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approach.","authors":"Dandan Liang, Jianing Zhang, Evan Chen, Zhe Li, Rui Li, Haibo Yang","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Split Federated Learning (SFL) enables scalable training on edge devices by combining the parallelism of Federated Learning (FL) with the computational offloading of Split Learning (SL). Despite its great success, SFL suffers significantly from the well-known straggler issue in distributed learning systems. This problem is exacerbated by the dependency between Split Server and clients: the Split Server side model update relies on receiving activations from clients. Such synchronization requirement introduces significant time latency, making straggler a critical bottleneck to the scalability and efficiency of the system. To mitigate this problem, we propose MU-SplitFed, a straggler-resilient SFL algorithm in zeroth-order optimization that decouples training progress from straggler delays via a simple yet effective unbalanced update mechanism. By enabling the server to perform <math><mi>τ</mi></math> local updates per client round, MU-SplitFed achieves a convergence rate of <math><mi>𝒪</mi> <mo>(</mo> <msqrt><mi>d</mi> <mo>/</mo> <mo>(</mo> <mi>τ</mi> <mi>T</mi> <mo>)</mo></msqrt> <mo>)</mo></math> for non-convex objectives, demonstrating a linear speedup of <math><mi>τ</mi></math> in communication rounds. Experiments demonstrate that MU-SplitFed consistently outperforms baseline methods with the presence of stragglers and effectively mitigates their impact through adaptive tuning of <math><mi>τ</mi></math> . The code for this project is available at https://github.com/Johnny-Zip/MU-SplitFed.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"31634-31673"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13225700/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148152353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Learning to Route: Per-Sample Adaptive Routing for Multimodal Multitask Prediction.","authors":"Marzieh Ajirak, Oded Bein, Ellen Rose Bowen, Dora Kanellopoulos, Avital Falk, Faith Gunning, Nili Solomonov, Logan Grosenick","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>We propose a unified framework for adaptive routing in multitask, multimodal prediction settings where data heterogeneity and task interactions vary across samples. We introduce a routing-based architecture that dynamically selects modality processing pathways and task-sharing strategies on a per-sample basis. Our model defines multiple modality paths, including raw and fused representations of text and numeric features, and learns to route each input through the most informative modality-task expert combination. Task-specific predictions are produced by shared or independent heads depending on the routing decision, and the entire system is trained end-to-end. We evaluate the model on both synthetic data and real-world psychotherapy notes, predicting depression and anxiety outcomes. Our experiments show that our method consistently outperforms fixed multitask or single-task baselines, and that the learned routing policy provides interpretable insights into modality relevance and task structure. This addresses critical challenges in personalized healthcare by providing per-subject adaptive information processing that accounts for data and task correlation heterogeneity.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"68521-68549"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13241019/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148201350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PolyPose: Deformable 2D/3D Registration via Polyrigid Transformations.","authors":"Vivek Gopalakrishnan, Neel Dey, Polina Golland","doi":"10.52202/085713-2026","DOIUrl":"10.52202/085713-2026","url":null,"abstract":"<p><p>Determining the 3D pose of a patient from a limited set of 2D X-ray images is a critical task in interventional settings. While preoperative volumetric imaging (e.g., CT and MRI) provides precise 3D localization and visualization of anatomical targets, these modalities cannot be acquired during procedures, where fast 2D imaging (X-ray) is used instead. To integrate volumetric guidance into intraoperative procedures, we present PolyPose, a simple and robust method for deformable 2D/3D registration. PolyPose parameterizes complex 3D deformation fields as a composition of rigid transforms, leveraging the biological constraint that individual bones do not bend in typical motion. Unlike existing methods that either assume no inter-joint movement or fail outright in this under-determined setting, our polyrigid formulation enforces anatomically plausible priors that respect the piecewise-rigid nature of human movement. This approach eliminates the need for expensive deformation regularizers that require patient- and procedure-specific hyperparameter optimization. Across extensive experiments on diverse datasets from orthopedic surgery and radiotherapy, we show that this strong inductive bias enables PolyPose to successfully align the patient's preoperative volume to as few as two X-rays, thereby providing crucial 3D guidance in challenging sparse-view and limited-angle settings where current registration methods fail. Additional visualizations, tutorials, and code are available at https://polypose.csail.mit.edu.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 2025","pages":"67454-67480"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13464490/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148725542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PoGDiff: Product-of-Gaussians Diffusion Models for Imbalanced Text-to-Image Generation.","authors":"Ziyan Wang, Sizhe Wei, Xiaoming Huo, Hao Wang","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Diffusion models have made significant advancements in recent years. However, their performance often deteriorates when trained or fine-tuned on imbalanced datasets. This degradation is largely due to the disproportionate representation of majority and minority data in image-text pairs. In this paper, we propose a general fine-tuning approach, dubbed PoGDiff, to address this challenge. Rather than directly minimizing the KL divergence between the predicted and ground-truth distributions, PoGDiff replaces the ground-truth distribution with a Product of Gaussians (PoG), which is constructed by combining the original ground-truth targets with the predicted distribution conditioned on a neighboring text embedding. Experiments on real-world datasets demonstrate that our method effectively addresses the imbalance problem in diffusion models, improving both generation accuracy and quality.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"138574-138604"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13198157/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148019017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Long-term Intracortical Neural activity and Kinematics (LINK): An intracortical neural dataset for chronic brain-machine interfaces, neuroscience, and machine learning.","authors":"Hisham Temmar, Yixuan Wang, Nina Gill, Nicholas B Mellon, Chang Liu, Luis Hernan Cubillos, Rio I Parsons, Joseph T Costello, Matteo Ceradini, Madison M Kelberman, Matthew J Mender, Aren I Hite, Dylan M Wallace, Samuel R Nason-Tomaszewski, Matthew S Willsey, Parag G Patil, Anne W Draelos, Cynthia A Chestek","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Intracortical brain-machine interfaces (iBMIs) have enabled movement and speech in people living with paralysis by using neural data to decode behaviors in real-time. However, intracortical neural recordings exhibit significant instabilities over time, which poses problems for iBMIs, neuroscience, and machine learning. For iBMIs, neural instabilities require frequent decoder recalibration to maintain high performance, a critical bottleneck for real-world translation. Several approaches have been developed to address this issue, and the field has recognized the need for standardized datasets on which to compare them, but no standard dataset exists for evaluation over year-long timescales. In neuroscience, a growing body of research attempts to elucidate the latent computations performed by populations of neurons. Nonstationarity in neural recordings imposes significant challenges to the design of these studies, so a dataset containing recordings over large time spans would improve methods to account for instabilities. In machine learning, continuous domain adaptation of temporal data is an area of active research, and a dataset containing shift distributions on long time scales would be beneficial to researchers. To address these gaps, we present the LINK Dataset (Long-term Intracortical Neural activity and Kinematics), which contains intracortical spiking activity and kinematic data from 312 sessions of a non-human primate performing a dexterous, 2 degree-of-freedom finger movement task, spanning 1,242 days. We also present longitudinal analyses of the dataset's neural spiking activity and its relationship to kinematics, as well as overall decoding performance using linear and neural network models. The LINK dataset and code are freely available to the public through the dataset website (https://chesteklab.github.io/LINK_dataset/).</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13322217/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148371022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A <i>Cautionary Tale</i> on Integrating Studies with Disparate Outcome Measures for Causal Inference.","authors":"Harsh Parikh, Trang Quynh Nguyen, Elizabeth A Stuart, Kara Rudolph, Caleb Miles","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Data integration approaches are increasingly used to enhance the efficiency and generalizability of studies. However, a key limitation of these methods is the assumption that outcome measures are identical across datasets - an assumption that often does not hold in practice. Consider the following opioid use disorder (OUD) studies: the XBOT trial and the POAT study, both evaluating the effect of medications for OUD on withdrawal symptom severity (not the primary outcome of either trial). While XBOT measures withdrawal severity using the subjective opiate withdrawal scale, POAT uses the clinical opiate withdrawal scale. We analyze this realistic yet challenging setting where outcome measures differ across studies and where neither study records both types of outcomes. Our paper studies whether and when integrating studies with disparate outcome measures leads to efficiency gains. We introduce three sets of assumptions - with varying degrees of strength - linking both outcome measures. Our theoretical and empirical results highlight a cautionary tale: integration can improve asymptotic efficiency only under the strongest assumption linking the outcomes. However, misspecification of this assumption leads to bias. In contrast, a milder assumption may yield finite-sample efficiency gains, yet these benefits diminish as sample size increases. We illustrate these trade-offs via a case study integrating the XBOT and POAT datasets to estimate the comparative effect of two medications for opioid use disorder on withdrawal symptoms. By systematically varying the assumptions linking the SOW and COW scales, we show potential efficiency gains and the risks of bias. Our findings emphasize the need for careful assumption selection when fusing datasets with differing outcome measures, offering guidance for researchers navigating this common challenge in modern data integration.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"28576-28595"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13196893/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148018934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective.","authors":"Thai-Hoang Pham, Jiayuan Chen, Seungyeon Lee, Yuanlong Wang, Sayoko Moroi, Xueru Zhang, Ping Zhang","doi":"10.52202/085713-4447","DOIUrl":"10.52202/085713-4447","url":null,"abstract":"<p><p>As machine learning (ML) algorithms are increasingly used in medical image analysis, concerns have emerged about their potential biases against certain social groups. Although many approaches have been proposed to ensure the fairness of ML models, most existing works focus only on medical image diagnosis tasks, such as image classification and segmentation, and overlooked prognosis scenarios, which involve predicting the likely outcome or progression of a medical condition over time. To address this gap, we introduce FairTTE, the first comprehensive framework for assessing fairness in time-to-event (TTE) prediction in medical imaging. FairTTE encompasses a diverse range of imaging modalities and TTE outcomes, integrating cutting-edge TTE prediction and fairness algorithms to enable systematic and fine-grained analysis of fairness in medical image prognosis. Leveraging causal analysis techniques, FairTTE uncovers and quantifies distinct sources of bias embedded within medical imaging datasets. Our large-scale evaluation reveals that bias is pervasive across different imaging modalities and that current fairness methods offer limited mitigation. We further demonstrate a strong association between underlying bias sources and model disparities, emphasizing the need for holistic approaches that target all forms of bias. Notably, we find that fairness becomes increasingly difficult to maintain under distribution shifts, underscoring the limitations of existing solutions and the pressing need for more robust, equitable prognostic models.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"147872-147930"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13485109/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148802235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond Scores: Proximal Diffusion Models.","authors":"Zhenghan Fang, Mateo Díaz, Sam Buchanan, Jeremias Sulam","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Diffusion models have quickly become some of the most popular and powerful generative models for high-dimensional data. The key insight that enabled their development was the realization that access to the score-the gradient of the log-density at different noise levels -allows for sampling from data distributions by solving a reverse-time stochastic differential equation (SDE) via forward discretization, and that popular denoisers allow for unbiased estimators of this score. In this paper, we demonstrate that an alternative, backward discretization of these SDEs, using proximal maps in place of the score, leads to theoretical and practical benefits. We leverage recent results in <i>proximal matching</i> to learn proximal operators of the log-density and, with them, develop Proximal Diffusion Models (ProxDM). Theoretically, we prove that <math> <mrow><mover><mi>𝒪</mi> <mo>~</mo></mover> <mo>(</mo> <mrow><mi>d</mi> <mrow><mo>∕</mo> <msqrt><mi>ε</mi></msqrt> </mrow> </mrow> <mo>)</mo></mrow> </math> steps suffice for the resulting discretization to generate an <math><mi>ε</mi></math> -accurate distribution w.r.t. the KL divergence. Empirically, we show that two variants of ProxDM achieve significantly faster convergence within just a few sampling steps compared to conventional score-matching methods.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"94483-94532"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13345691/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148413949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}