Advances in neural information processing systems最新文献

{"title":"Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks.","authors":"Ann Huang, Satpreet H Singh, Flavio Martinelli, Kanaka Rajan","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Task-trained recurrent neural networks (RNNs) are widely used in neuroscience and machine learning to model dynamical computations. To gain mechanistic insight into how neural systems solve tasks, prior work often reverse-engineers individual trained networks. However, different RNNs trained on the same task and achieving similar performance can exhibit strikingly different internal solutions, a phenomenon known as solution degeneracy. Here, we develop a unified framework to systematically quantify and control solution degeneracy across three levels: behavior, neural dynamics, and weight space. We apply this framework to 3,400 RNNs trained on four neuroscience-relevant tasks-flip-flop memory, sine wave generation, delayed discrimination, and path integration-while systematically varying task complexity, learning regime, network size, and regularization. We find that higher task complexity and stronger feature learning reduce degeneracy in neural dynamics but increase it in weight space, with mixed effects on behavior. In contrast, larger networks and structural regularization reduce degeneracy at all three levels. These findings empirically validate the Contravariance Principle and provide practical guidance for researchers seeking to tune the variability of RNN solutions, either to uncover shared neural mechanisms or to model the individual variability observed in biological systems. This work provides a principled framework for quantifying and controlling solution degeneracy in task-trained RNNs, offering new tools for building more interpretable and biologically grounded models of neural computation.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"105259-105304"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13151944/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147870768","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":"POCO: Scalable Neural Forecasting through Population Conditioning.","authors":"Yu Duan, Hamza Tahir Chaudhry, Misha B Ahrens, Christopher D Harvey, Matthew G Perich, Karl Deisseroth, Kanaka Rajan","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Predicting future neural activity is a core challenge in modeling brain dynamics, with applications ranging from scientific investigation to closed-loop neurotechnology. While recent models of population activity emphasize interpretability and behavioral decoding, neural forecasting-particularly across multi-session, spontaneous calcium recordings-remains underexplored. We introduce POCO, a unified forecasting model that combines a lightweight univariate forecaster with a population-level encoder to capture both neuron-specific and brain-wide dynamics in calcium imaging recordings. Trained across five calcium imaging datasets spanning zebrafish, mice, and <i>C. elegans,</i> POCO achieves state-of-the-art accuracy at cellular resolution in spontaneous behaviors. After pre-training, POCO rapidly adapts to new recordings with minimal fine-tuning. Notably, POCO's learned unit embeddings recover biologically meaningful structure-such as brain region clustering-without any anatomical labels. Our comprehensive analysis reveals several key factors influencing performance, including context length, session diversity, and preprocessing. Together, these results position POCO as a scalable and adaptable approach for cross-session neural forecasting and offer actionable insights for future model design. By enabling accurate, generalizable forecasting models of neural dynamics across individuals and species, POCO lays the groundwork for adaptive neurotechnologies and large-scale efforts for neural foundation models. Code is available at https://github.com/yuvenduan/POCO.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"23631-23669"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13151936/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147870805","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":"Covariate-moderated Empirical Bayes Matrix Factorization.","authors":"William R P Denault, Karl Tayeb, Peter Carbonetto, Matthew Stephens, Jason Willwerscheid","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Matrix factorization is a fundamental method in statistics and machine learning for inferring and summarizing structure in multivariate data. Modern data sets often come with \"side information\" of various forms (images, text, graphs) that can be leveraged to improve estimation of the underlying structure. However, existing methods that leverage side information are limited in the types of data they can incorporate, and they assume specific parametric models. Here, we introduce a novel method for this problem, <i>covariate-moderated empirical Bayes matrix factorization</i> (cEBMF). cEBMF is a modular framework that accepts any type of side information that is processable by a probabilistic model or a neural network. The cEBMF framework can accommodate different assumptions and constraints on the factors through the use of different priors, and it adapts these priors to the data. We demonstrate the benefits of cEBMF in simulations and in analyses of spatial transcriptomics and collaborative filtering data. A PyTorch-based implementation of cEBMF with flexible priors is available at https://github.com/william-denault/cebmf_torch.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"47219-47250"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13353771/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148427072","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":"Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning.","authors":"Ke Sun, Yingnan Zhao, Enze Shi, Yafei Wang, Xiaodong Yan, Bei Jiang, Linglong Kong","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>The remarkable empirical performance of distributional reinforcement learning (RL) has garnered increasing attention to understanding its theoretical advantages over classical RL. By decomposing the categorical distributional loss commonly employed in distributional RL, we find that the potential superiority of distributional RL can be attributed to a derived distribution-matching entropy regularization. This less-studied entropy regularization aims to capture additional knowledge of return distribution beyond only its expectation, contributing to an augmented reward signal in policy optimization. In contrast to the vanilla entropy regularization in MaxEnt RL, which explicitly encourages exploration by promoting diverse actions, the novel entropy regularization derived from categorical distributional loss implicitly updates policies to align the learned policy with (estimated) environmental uncertainty. Finally, extensive experiments verify the significance of this uncertainty-aware regularization from distributional RL on the empirical benefits over classical RL. Our study offers an innovative exploration perspective to explain the intrinsic benefits of distributional learning in RL.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"157271-157308"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13345479/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148413974","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":"Inference of Whole Brain Electrophysiological Networks Through Multimodal Integration of Simultaneous Scalp and Intracranial EEG.","authors":"Shihao Yang, Feng Liu","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Brain imaging research has transitioned over the past decades from identifying isolated regions of task-evoked activation to characterizing the spatiotemporal dynamics of large-scale brain networks. Electrophysiological signals are the direct manifestation of brain activity; thus, characterizing whole-brain electrophysiological networks (WBEN) can serve as a fundamental tool for neuroscience studies and clinical applications. In this work, we introduce a framework for integrating scalp EEG and intracranial EEG (iEEG) for WBEN estimation through a principled state-space modeling approach, where an Expectation-Maximization (EM) algorithm is designed to infer the state va riables and brain connectivity simultaneously. We validated the proposed method on synthetic data, and the results revealed improved performance compared to traditional two-step methods using scalp EEG only, demonstrating the importance of including iEEG signals for WBEN estimation. For real data with simultaneous EEG and iEEG, we applied the developed framework to understand the information flows during encoding and maintenance phases of a working memory task. The information flows between subcortical and cortical regions are delineated, highlighting more significant information flows from cortical to subcortical regions during encoding than during maintenance. The results are consistent with previous research findings, but from a whole-brain perspective, which underscores the unique utility of the proposed framework.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"90686-90712"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13345474/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148413960","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":"BaRISTA: Brain Scale Informed Spatiotemporal Representation of Human Intracranial Neural Activity.","authors":"Lucine L Oganesian, Saba Hashemi, Maryam M Shanechi","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Intracranial recordings have opened a unique opportunity to simultaneously measure activity across multiregional networks in the human brain. Recent works have focused on developing transformer-based neurofoundation models of such recordings that can generalize across subjects and datasets. However, these recordings exhibit highly complex spatiotemporal interactions across diverse spatial scales, from the single-channel scale to the scale of brain regions. As such, there remain critical open questions regarding how best to encode spatial information and how to design self-supervision tasks that enable the learning of brain network patterns and enhance downstream decoding performance using such high-dimensional, multiregional recordings. To allow for exploring these questions, we propose a new spatiotemporal transformer model of multiregional neural activity and a corresponding self-supervised masked latent reconstruction task, designed to enable flexibility in the spatial scale used for token encoding and masking. Applying this model on publicly available multiregional intracranial electrophysiology (iEEG) data, we demonstrate that adjusting the spatial scale for both token encoding and masked reconstruction significantly impacts downstream decoding. Further, we find that spatial encoding at larger scales than channel-level encoding, which is commonly used in existing iEEG transformer models, improves downstream decoding performance. Finally, we demonstrate that our method allows for region-level token encoding while also maintaining accurate channel-level neural reconstruction. Taken together, our modeling framework enables exploration of the spatial scales used for token encoding and masking, reveals their importance towards self-supervised pretraining of neurofoundation models of multiregional human brain activity, and enhances downstream decoding performance.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"185289-185322"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13521586/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148842422","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":"Distributionally Robust Feature Selection.","authors":"Maitreyi Swaroop, Tamar Krishnamurti, Bryan Wilder","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>We study the problem of selecting limited features to observe such that models trained on them can perform well simultaneously across multiple subpopulations. This problem has applications in settings where collecting each feature is costly, e.g. requiring adding survey questions or physical sensors, and we must be able to use the selected features to create high-quality downstream models for different populations. Our method frames the problem as a continuous relaxation of traditional variable selection using a noising mechanism, without requiring back-propagation through model training processes. By optimizing over the variance of a Bayes-optimal predictor, we develop a model-agnostic framework that balances overall performance of downstream prediction across populations. We validate our approach through experiments on both synthetic datasets and real-world data.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"63046-63075"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13298188/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148347445","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":"STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology.","authors":"Barathi Subramanian, Rathinaraja Jeyaraj, Mitchell Nevin Peterson, Terry Guo, Nigam Shah, Curtis Langlotz, Andrew Y Ng, Jeanne Shen","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Multi-class tissue-type classification of colorectal cancer (CRC) histopathologic images is a significant step in the development of downstream machine learning models for diagnosis and treatment planning. However, publicly available CRC datasets used to build tissue classifiers often suffer from insufficient morphologic diversity, class imbalance, and low-quality image tiles, limiting downstream model performance and generalizability. To address this research gap, we introduce STARC-9 (STAnford coloRectal Cancer), a large-scale dataset for multi-class tissue classification. STARC-9 comprises 630,000 histopathologic image tiles uniformly sampled across nine clinically relevant tissue classes (each represented by 70,000 tiles), systematically extracted from hematoxylin & eosin-stained whole-slide images (WSI) from 200 CRC patients at the Stanford University School of Medicine. To construct STARC-9, we propose a novel framework, DeepCluster++, consisting of two primary steps to ensure diversity within each tissue class, followed by pathologist verification. First, an encoder from an autoencoder trained specifically on histopathologic images is used to extract feature vectors from all tiles within a given input WSI. Next, K-means clustering groups morphologically similar tiles, followed by an equal-frequency binning method to sample diverse patterns within each tissue class. Finally, the selected tiles are verified by expert gastrointestinal pathologists to ensure classification accuracy. This semi-automated approach significantly reduces the manual effort required for dataset curation while producing high-quality training examples. To validate the utility of STARC-9, we benchmarked baseline convolutional neural networks, transformers, and pathology-specific foundation models on downstream multi-class CRC tissue classification and segmentation tasks when trained on STARC-9 versus publicly available datasets, demonstrating superior generalizability of models trained on STARC-9. Although we demonstrate the utility of DeepCluster++ on CRC as a pilot use-case, it is a flexible framework that can be used for constructing high-quality datasets from large WSI repositories across a wide range of cancer and non-cancer applications. https://huggingface.co/datasets/Path2AI/STARC-9/tree/main https://github.com/Path2AI/STARC-9/.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13138521/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147846694","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":"Cross-Modal Representational Knowledge Distillation for Enhanced Spike-Informed LFP Modeling.","authors":"Eray Erturk, Saba Hashemi, Maryam M Shanechi","doi":"10.52202/085713-1792","DOIUrl":"10.52202/085713-1792","url":null,"abstract":"<p><p>Local field potentials (LFPs) can be routinely recorded alongside spiking activity in intracortical neural experiments, measure a larger complementary spatiotemporal scale of brain activity for scientific inquiry, and can offer practical advantages over spikes, including greater long-term stability, robustness to electrode degradation, and lower power requirements. Despite these advantages, recent neural modeling frameworks have largely focused on spiking activity since LFP signals pose inherent modeling challenges due to their aggregate, population-level nature, often leading to lower predictive power for downstream task variables such as motor behavior. To address this challenge, we introduce a cross-modal knowledge distillation framework that transfers high-fidelity representational knowledge from pretrained multi-session spike transformer models to LFP transformer models. Specifically, we first train a teacher spike model across multiple recording sessions using a masked autoencoding objective with a session-specific neural tokenization strategy. We then align the latent representations of the student LFP model to those of the teacher spike model. Our results show that the Distilled LFP models consistently outperform single- and multi-session LFP baselines in both fully unsupervised and supervised settings, and can generalize to other sessions without additional distillation while maintaining superior performance. These findings demonstrate that cross-modal knowledge distillation is a powerful and scalable approach for leveraging high-performing spike models to develop more accurate LFP models.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"59798-59843"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13521591/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148842359","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":"Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time.","authors":"Daniel D Richman, Jessica Karaguesian, Carl-Mikael Suomivuori, Ron O Dror","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>The function of biomolecules such as proteins depends on their ability to interconvert between a wide range of structures or \"conformations.\" Researchers have endeavored for decades to develop computational methods to predict the distribution of conformations, which is far harder to determine experimentally than a static folded structure. We present ConforMix, an inference-time algorithm that enhances sampling of conformational distributions using a combination of classifier guidance, filtering, and free energy estimation. Our approach upgrades diffusion models-whether trained for static structure prediction or conformational generation-to enable more efficient discovery of conformational variability without requiring prior knowledge of major degrees of freedom. ConforMix is orthogonal to improvements in model pretraining and would benefit even a hypothetical model that perfectly reproduced the Boltzmann distribution. Remarkably, when applied to a diffusion model trained for static structure prediction, ConforMix captures structural changes including domain motion, cryptic pocket flexibility, and transporter cycling, while avoiding unphysical states. Case studies of biologically critical proteins demonstrate the scalability, accuracy, and utility of this method.</p>","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"167662-167682"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13293296/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148334822","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}