论文检索

Applications · Neuroscience, Cognitive Science

Wu S. Zihan, Ariane Delrocq, Wulfram Gerstner, Guillaume Bellec

While end-to-end self-supervised learning with backpropagation (global BP-SSL) has become central for training modern AI systems, theories of local self-supervised learning (local-SSL) have struggled to build functional representations in deep neural networks. To establish a link between global and local rules, we first develop a theory for deep linear networks: We identify conditions for local-SSL algorithms (like Forward-forward or CLAPP) to implement exactly the same weight update as a global BP-SSL. Starting from the theoretical insights, we then develop novel variants of local-SSL algorithms to approximate global BP-SSL in deep non-linear convolutional neural networks. Variants that improve the similarity between updates of local-SSL with those of global BP-SSL also show better performance on image datasets (CIFAR-10, STL-10, and Tiny ImageNet). The best local-SSL rule with the CLAPP loss function matches the performance of a comparable global BP-SSL with InfoNCE or CPC-like loss functions, and improves upon state-of-the-art for layer-wise SSL on these benchmarks.

Theory · Learning Theory

Yuanfan Li, Xiyuan Wei, Tianbao Yang, Yiming Ying

Contrastive representation learning (CRL) underpins many modern foundation models. Despite recent theoretical progress, existing analyses suffer from several key limitations: (i) the statistical consistency of CRL remains poorly understood; (ii) available generalization bounds deteriorate as the number of negative samples increases, contradicting the empirical benefits of large negative sets; and (iii) the retrieval performance of CRL has received limited theoretical attention. In this paper, we develop a unified statistical learning theory for CRL. For downstream tasks, we evaluate retrieval quality using an AUC-type population criterion and show that the contrastive loss is *statistically consistent* with optimal ranking. We further establish a *calibration-style inequality* that quantitatively relates excess contrastive risk to excess retrieval suboptimality. For upstream training, we study both supervised and self-supervised contrastive objectives and derive generalization bounds of order $O(1/m + 1/\sqrt{n})$ and $O(1/\sqrt{m} + 1/\sqrt{n})$, respectively, where $m$ denotes the number of negative samples and $n$ the number of anchor points. These bounds not only explain the empirical advantages of large negative sets but also reveal an explicit trade-off between $m$ and $n$. Extensive experiments on large-scale vision--language models corroborate our theoretical predictions.

Deep Learning · Self-Supervised Learning

Faris Chaudhry

We develop a geometric theory of projection heads in self-supervised learning by interpreting the head as a trainable metric on the backbone representation manifold. Our analysis reveals that head curvature and architectural asymmetry induce negative eigenvalues of the Hessian at collapsed equilibria in networks with smooth activation functions, yielding a destabilization mechanism which explains collapse avoidance in non-contrastive methods. We further show that linear heads perform implicit subspace whitening under induced metric geometry, while nonlinear heads adapt local metrics to satisfy the specific topological constraints of the loss. Finally, we characterize how metric degeneracy governs the information-invariance trade-off in learned representations. Our results apply to both contrastive and non-contrastive objectives including InfoNCE, BYOL, SimSiam, and decorrelation-based methods, demonstrating that the projection head acts as a universal geometric buffer that decouples the semantic backbone from the rigid constraints of the training objective.

Deep Learning · Generative Models and Autoencoders

Xiaoyan Xing, Xiao Zhang, Sezer Karaoglu, Theo Gevers, Anand Bhattad

Image-to-image relighting requires representations that disentangle scene properties from illumination. Recent methods rely on latent intrinsic representations but remain under-constrained and often fail on challenging materials such as metal and glass. A natural hypothesis is that stronger pretrained visual priors should resolve these failures. We find the opposite: features from top-performing semantic encoders often degrade relighting quality, revealing a fundamental trade-off between semantic abstraction and photometric fidelity. We study this trade-off and introduce Augmented Latent Intrinsics (ALI), which balances semantic context and dense photometric structure by fusing features from a pixel-aligned visual encoder into a latent-intrinsic framework, together with a self-supervised refinement strategy to mitigate the scarcity of paired real-world data. Trained only on unlabeled real-world image pairs and paired with a dense, pixel-aligned visual prior, ALI achieves strong relighting improvements, with the largest gains on complex, specular materials.

Applications · Computer Vision

Qingdong He, Chaoyi Wang, Peng TANG, Yifan Yang, Xiaobin Hu

Video subtitle removal is essential for content localization and media re-editing, yet existing mask-guided diffusion methods face critical limitations: training inefficiency requiring extensive annotations and full model fine-tuning, inference complexity demanding explicit mask sequences, and static prior utilization unable to adapt to quality variations. We present CLEAR (Context-aware Learning for End-to-end Adaptive subtitle Removal), a lightweight adapter-based framework addressing these challenges through three technical innovations. First, self-supervised prior learning (Stage I) extracts occlusion guidance from video pairs using pixel differences as weak supervision, eliminating annotation dependency while learning generalizable subtitle features across languages. Second, LoRA-based adaptive refinement (Stage II) enables parameter-efficient training that preserves pre-trained visual priors while achieving true mask-free end-to-end inference without external detection modules. Third, adaptive focal weighting dynamically adjusts prior influence based on local quality assessment, effectively handling diverse subtitle styles and noisy guidance signals. Extensive experiments demonstrate CLEAR's superior performance in multilingual subtitle removal while requiring only 0.77% trainable parameters, establishing a new paradigm for efficient video text removal without inference-time mask dependencies.

Deep Learning · Self-Supervised Learning

Jie Chen, Zhu Wang, Chuanbin Liu, Xi Peng

Features of the same sample generated by different pretrained models often exhibit inherently distinct feature distributions. Learning invariant representations from large-scale unlabeled visual data with various pretrained models in a fully unsupervised transfer manner remains a significant challenge. In this paper, we propose a multiview self-representation learning (MSRL) method in which invariant representations are learned by exploiting the self-representation property of features across heterogeneous views. The features are derived from large-scale unlabeled visual data through transfer learning with various pretrained models and are referred to as heterogeneous multiview data. We introduce an information-passing mechanism that relies on self-representation learning to support feature aggregation over the outputs of the linear model. Moreover, an assignment probability distribution consistency scheme is presented to guide multiview self-representation learning by exploiting complementary information across different views. Consequently, representation invariance across different linear models is enforced through this scheme. In addition, we provide a theoretical analysis of the assignment probability distribution consistency and incremental views. Extensive experiments with multiple benchmark visual datasets demonstrate that the proposed MSRL method consistently outperforms several state-of-the-art approaches.

Applications · Neuroscience, Cognitive Science

Jinhan Liu, Mahsa Shoaran

Affective and cognitive disorders manifest as distributed, time-varying brain network dynamics across regions, channels, and time, challenging robust representation learning from EEG/sEEG for clinical diagnosis. We propose **RECTOR** (Masked **Re**gion–**C**hannel–**T**emp**or**al Modeling), an end-to-end self-supervised framework that unifies joint region-channel-temporal representation learning beyond fixed anatomical priors. At its core, **RECTOR-SA** is a hierarchical, block-sparse self-attention induced by Adaptive Functional Partitioning that evolves region structures from static anatomical definitions to adaptive functional regions. The self-supervision is driven by **Masked Topology and Representation Learning**, which jointly optimizes three complementary objectives: Masked Predictive Modeling, Topological Structure Modeling, and Cross-View Consistency. Across diverse benchmarks, RECTOR sets a new state-of-the-art in EEG emotion recognition and sEEG task-engagement classification. Crucially, its strong robustness to missing channels and cross-montage generalization underscores its potential for large-scale pre-training on heterogeneous EEG/sEEG, providing interpretable insights at both region and channel levels.

Deep Learning · Self-Supervised Learning

Yongchao Huang

Joint Embedding Predictive Architectures (JEPA) offer a scalable paradigm for self-supervised learning by predicting latent representations rather than reconstructing high-entropy observations. However, existing formulations rely on deterministic regression objectives, which masks probabilistic semantics and limits its applicability in stochastic control. We introduce \emph{Variational JEPA (VJEPA)}, a probabilistic generalization that learns a predictive distribution over future latent states via a variational objective. We show that VJEPA unifies representation learning with Predictive State Representations (PSRs) and Bayesian filtering, establishing that sequential modeling does not require autoregressive observation likelihoods. Theoretically, we prove that VJEPA representations serve as sufficient information states for optimal control without pixel reconstruction, while providing formal guarantees for collapse avoidance. We further propose \emph{Bayesian JEPA (BJEPA)}, which extends the VJEPA framework to factorize predictive belief into a learned dynamics expert and a modular prior expert, enabling zero-shot task transfer and constraints satisfactions (e.g., goals, physics) via a Product of Experts. Empirically, VJEPA filters out high-variance nuisance distractors that cause representation collapse in generative baselines. By enabling principled uncertainty estimation (e.g. constructing credible intervals via sampling) while remaining likelihood-free regarding observations, VJEPA provides a foundational framework for scalable, robust, uncertainty-aware planning in high-dimensional, noisy environments.

Deep Learning · Self-Supervised Learning

Maedeh Zarvandi, Michael Timothy, Theresa Wasserer, Debarghya Ghoshdastidar

Self-supervised learning (SSL) effectively learns representations from massive unlabeled data, yet the resulting models typically operate as black boxes, necessitating domain-specific post-hoc explanations. We introduce KREPES, a unified framework that learns inherently interpretable representations for arbitrary SSL objectives, including SimCLR, BYOL, VICReg. By bridging empirical neural tangent kernel approximations of neural networks with the Representer Theorem for kernels, we express the learned latent space directly via "Representer Landmarks", which are the representations of influential unlabeled training examples. We introduce two novel metrics, "Sample-Specific Influence Score" and "Conceptual Influence Profile", to quantify the transparency of the learned representations. KREPES enables direct audit of the latent space without supervision, for example, revealing an algorithmic bias in the Adult-1M dataset where SSL uses demographic proxies for income. Finally, to ensure scalability to SSL benchmarks with 1M+ samples (ImageNet-1K, Adult-1M), KREPES introduces a novel Nyström approximation-based optimization of any non-convex SSL objective.

Deep Learning · Self-Supervised Learning

Jiaxin Sun, Yuhua Qian, Yang Wang

Standard contrastive learning minimizes geometric distance between positive pairs, implicitly assuming that strict compactness optimizes discrimination. However, this topology-agnostic confusion neglects intrinsic data structures and topological complexity, leading to class confusion—particularly when aggressive augmentations induce semantic drift. To address this, we propose Topology-Aware Contrastive Learning, a framework that shifts the objective from geometric singularity to topological connectivity. Leveraging Persistent Homology, we explicitly regulate the connectivity of the latent space, ensuring positive pairs maintain an α–β that balances intra-class cohesion with separability. Theoretically, we formally define the topology-agnostic confusion phenomenon, prove that excessive compactness strictly lower-bounds the probability of confusion and derive a generalization bound demonstrating that richer topological connectivity tightens downstream risk. Furthermore, we establish a measure-theoretic framework to mitigating the sensitivity of our method against varying augmentation strengths. Empirical results on benchmarks confirm that our approach enhances representation quality and reduces reliance on specific augmentation strategies compared to standard baselines. Our code will be made publicly available upon acceptance.

Deep Learning · Self-Supervised Learning

Yaoqi Liu, Jin Wang, Chunchen Wang, Hui Wang, Chuan Shi

In recent years, wireless signal recognition (WSR), which leverages artificial intelligence (AI) to identify properties of passively received radio signals, has garnered significant attention due to its broad applications, such as spectrum management. Existing WSR methods typically learn directly from received signals, which are distorted by physical wireless channel effects such as fading, and current denoising diffusion models lack de-channeling capabilities, which leads to performance degradation. Therefore, we propose PWC-Diff, a novel framework that integrates prior Physical Wireless Channels into the denoising Diffusion process. The framework employs a dedicated architecture named FusedFormer, which contains a fusion module and a self-attention module that jointly capture the temporal and spectral characteristics of the signals throughout the diffusion trajectory. By leveraging prior wireless channels, PWC-Diff learns to progressively “de-channel” the received signal and recover a representation closer to the transmitted signal. Extensive experiments on several datasets across three WSR tasks have achieved state-of-the-art (SOTA) performance, which demonstrates the rationality of our theory, and ablation experiments further illustrate the effectiveness of our proposed PWC-Diff.

Deep Learning · Self-Supervised Learning

Julie Mordacq, Vicky Kalogeiton, Steve Oudot

Self-supervised learning (SSL) has emerged as a powerful paradigm for learning meaningful representations from unlabeled data. However, the standard protocol for evaluating these representations, linear probing, is computationally expensive, sensitive to hyperparameters, and provides limited insight into the geometric structure of the representation space. In this work, motivated by connections between neural network generalization and intrinsic dimensionality (ID) we propose IdEst, a method for estimating the ID of SSL representations via the Minimum Spanning Tree dimension estimator ($\mathrm{dim}_\mathrm{MST}$). Across diverse datasets, architectures, and SSL pretraining objectives, we show that IdEst strongly correlates withdownstream linear probe performances. Furthermore, we demonstrate that IdEst enables efficient hyperparameter selection, significantly reducing the computational cost compared to supervised alternatives. Our results highlight intrinsic dimensionality as a principled geometric proxy for assessing and optimizing SSL representations, complementing standard supervised probing protocols.

Deep Learning · Self-Supervised Learning

Achleshwar Luthra, Yash Salunkhe, Tomer Galanti

Frozen self-supervised representations often transfer well with only a few labels across many semantic tasks. We argue that a single geometric quantity, *directional* CDNV (decision-axis variance), sits at the core of two favorable behaviors: strong few-shot transfer within a task, and low interference across many tasks. We show that both emerge when variability *along* class-separating directions is small. First, we prove sharp non-asymptotic multiclass generalization bounds for downstream classification whose leading term is the directional CDNV. The bounds include finite-shot corrections that cleanly separate intrinsic decision-axis variability from centroid-estimation error. Second, we link decision-axis collapse to multitask geometry: for independent balanced labelings, small directional CDNV across tasks forces the corresponding decision axes to be nearly orthogonal, helping a single representation support many tasks with minimal interference. Empirically, across SSL objectives, directional CDNV collapses during pretraining even when classical CDNV remains large, and our bounds closely track few-shot error at practical shot sizes. Additionally, on synthetic multitask data, we verify that SSL learns representations whose induced decision axes are nearly orthogonal.

Deep Learning · Self-Supervised Learning

Ziwei Li, Shuzi Niu, Tao Yuan, Huiyuan Li

The performance of sparse direct solvers is fundamentally governed by fill-in, i.e. new nonzero entries arising from the LU factorization of a sparse matrix, as they dictate memory footprint and subsequent computation time. For decades, a variety of graph-theoretic algorithms have aimed to minimize fill-in, a problem known to be both NP-hard and critically important. While recent deep learning methods, optimizing surrogate fill-in objectives, show empirical promise and can outperform classical algorithms on certain matrices, they offer limited interpretability into the underlying mechanism of fill-in generation. To address this, we propose a novel reordering approach, Causal Triplet Structure Learning (CTS), which is grounded in the Fill-Path Theorem and reduces arbitrary-length fill-paths to length-two candidate triplets, identifies the causal structures that trigger fill-in, and intervenes to block their formation. Empirically, we design a multigrid-style GAT with KAN activations to learn vertex embeddings and introduce a causal triplet loss that discourages such structures during training. Experiments on the SuiteSparse Matrix Collection demonstrate that our method reduces fill-in by 6$\times$, leading to 12$\times$ speedup in factorization time compared to state-of-the-art methods on Chemical Process Simulation and Computational Fluid Dynamics matrices.

Justinas Zaliaduonis, Sergios Gatidis, Till Richter, Patrick Putzky

Contrastive learning has emerged as a powerful paradigm for self-supervised representation learning, yet the precise conditions under which it recovers meaningful latent structure remain incompletely understood. We develop a measure-theoretic framework that formalizes the diversity condition, a requirement on the sampling mechanism that is necessary for recovering the latent space up to orthogonal transformation. We prove that when this condition is violated, as commonly occurs in practical settings where augmentations preserve semantic content, the optimal encoder no longer preserves geometric structure and linear identifiability is lost. Crucially, we demonstrate that the contrastive loss alone is insufficient for latent space reconstruction: encoder inductive bias emerges as a critical component that compensates for violations of the diversity condition. Our experiments on synthetic datasets and CIFAR-10 confirm these theoretical predictions, showing that architectural constraints become essential precisely when sampling diversity is limited. These findings have direct implications for the design of data augmentation strategies and encoder architectures in self-supervised contrastive learning systems.

Applications · Health / Medicine

Maxence Gélard, Hakim Benkirane, Thomas Pierrot, Guillaume Richard, Paul-Henry Cournède

Oncologists are increasingly relying on multiple modalities to model the complexity of diseases. Within this landscape, transcriptomic and epigenetic data have proven to be particularly instrumental and play an increasingly vital role in clinical applications. However, their integration into multimodal models remains a challenge, especially considering their high dimensionality. In this work, we present a novel bimodal model that jointly learns representations of bulk RNA-seq and DNA methylation leveraging self-supervision from masked language modeling. We leverage an architecture that reduces the memory footprint usually attributed to purely transformer-based models when dealing with long sequences. We demonstrate that the obtained bimodal embeddings can be used to fine-tune cancer-type classification and survival models that achieve state-of-the-art performance compared to unimodal models. Furthermore, we introduce a robust learning framework that maintains downstream task performance despite missing modalities, enhancing the model’s applicability in real-world clinical settings.

Reinforcement Learning · Batch/Offline

Marco Bagatella, Mert Albaba, Jonas Hübotter, Georg Martius, Andreas Krause

Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There are strong parallels between this widespread framework and offline goal-conditioned reinforcement learning algorithms: a universal value function is trained on a large number of goals, and the policy is evaluated on a single goal in each test episode. Extensive research in foundation models has shown that performance can be substantially improved through test-time training, specializing the model to the current goal. We find similarly that test-time offline reinforcement learning on experience related to the test goal can lead to substantially better policies at modest compute costs. We propose a novel self-supervised data selection criterion, which selects transitions from an offline dataset according to their relevance to the current state and quality with respect to the evaluation goal. We demonstrate across a wide range of high-dimensional loco-navigation and manipulation tasks that fine-tuning a policy on the selected data for a few gradient steps leads to significant performance gains over standard offline pre-training. Our goal-conditioned test-time training (GC-TTT) algorithm applies this routine in a receding-horizon fashion during evaluation, adapting the policy to the current trajectory as it is being rolled out. Finally, we study compute allocation at inference, demonstrating that, at comparable costs, GC-TTT induces performance gains that are not achievable by scaling model size.

Deep Learning · Large Language Models

Yuri Kuratov, Matvey Kairov, Aydar Bulatov, Ivan Rodkin, Mikhail Burtsev

Many large language model applications require conditioning on long contexts. Transformers typically support this by storing a large per-layer KV-cache of past activations, which incurs substantial memory overhead. A desirable alternative is compressive memory: read a context once, store it in a compact state, and answer many queries from that state. We study this in a context removal setting, where the model must generate an answer without access to the original context at inference time. We introduce GradMem, which writes context into memory via per-sample test-time optimization. Given a context, GradMem performs a few steps of gradient descent on a small set of prefix memory tokens while keeping model weights frozen. GradMem explicitly optimizes a model-level self-supervised context reconstruction loss, resulting in a loss-driven write operation with iterative error correction, unlike forward-only methods. On associative key--value retrieval, GradMem outperforms forward-only memory writers with the same memory size, and additional gradient steps scale capacity much more effectively than repeated forward writes. We further show that GradMem transfers beyond synthetic benchmarks: with pretrained language models, it attains competitive results on natural language tasks including bAbI and SQuAD variants, relying only on information encoded in memory.

Deep Learning · Self-Supervised Learning

Yi Liu, Hongji Zhang, Yiwen Wang, Dimitrios Tsaras, Lei Chen, Mingxuan Yuan, Qiang Xu

Estimating the quality of register transfer level (RTL) designs is crucial in the electronic design automation (EDA) workflow, as it enables instant feedback on key performance metrics like area and delay without the need for time-consuming logic synthesis. While recent approaches have leveraged large language models (LLMs) to derive embeddings from RTL code and achieved promising results, they overlook the structural semantics essential for accurate quality estimation. In contrast, the control data flow graph (CDFG) view exposes the design's structural characteristics more explicitly, offering richer cues for representation learning. In this work, we introduce StructRTL, a novel structure-aware graph self-supervised learning framework for improved RTL design quality estimation. By learning structure-informed representations from CDFGs, StructRTL significantly outperforms prior art on various quality estimation tasks. To further boost performance, we incorporate a knowledge distillation strategy that transfers low-level insights from post-mapping netlists into the CDFG-based predictor. Experimental results demonstrate that StructRTL establishes new state-of-the-art results, highlighting the effectiveness of combining structural learning with cross-stage supervision.

Deep Learning · Self-Supervised Learning

Moritz Gögl, Christopher Yau

The Joint-Embedding Predictive Architecture (JEPA) is often seen as a non-generative alternative to likelihood-based self-supervised learning, emphasizing prediction in representation space rather than reconstruction in observation space. We argue that the resulting separation from probabilistic generative modeling is largely rhetorical rather than structural: the canonical JEPA design–coupled encoders with a context-to-target predictor–mirrors the variational posteriors and learned conditional priors obtained when variational inference is applied to a particular class of coupled latent-variable models, and standard JEPA can be viewed as a deterministic specialization in which regularization is imposed via architectural and training heuristics rather than an explicit likelihood. Building on this view, we derive the Variational JEPA (Var-JEPA), which makes the latent generative structure explicit by optimizing a single Evidence Lower Bound (ELBO). This yields meaningful representations without ad-hoc anti-collapse regularizers and allows principled uncertainty quantification in the latent space. We instantiate the framework for tabular data (Var-T-JEPA) and achieve strong representation learning and downstream performance, consistently improving over T-JEPA while remaining competitive with strong raw-feature baselines.