Deep learning · self supervised learning

Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic driving emerges entirely from self-play in simulation at unprecedented scale -- 1.6 billion km of driving. This is enabled by Gigaflow, a batched simulator that can synthesize and train on 42 years of subjective driving experience per hour on a single 8-GPU node. The resulting policy achieves state-of-the-art performance on three independent autonomous driving benchmarks. The policy outperforms the prior state of the art when tested on recorded real-world scenarios, amidst human drivers, without ever seeing human data during training. The policy is realistic when assessed against human references and achieves unprecedented robustness, averaging 17.5 years of continuous driving between incidents in simulation.

Defending Graph Neural Networks (GNNs) against adversarial attacks requires balancing accuracy and robustness, a trade-off often mishandled by traditional methods like adversarial training that intertwine these conflicting objectives within a single classifier. To overcome this limitation, we propose a self-supervised adversarial purification framework. We separate robustness from the classifier by introducing a dedicated purifier, which cleanses the input data before classification. In contrast to prior adversarial purification methods, we propose GPR-GAE, a novel graph auto-encoder (GAE), as a specialized purifier trained with a self-supervised strategy, adapting to diverse graph structures in a data-driven manner. Utilizing multiple Generalized PageRank (GPR) filters, GPR-GAE captures diverse structural representations for robust and effective purification. Our multi-step purification process further facilitates GPR-GAE to achieve precise graph recovery and robust defense against structural perturbations. Experiments across diverse datasets and attack scenarios demonstrate the state-of-the-art robustness of GPR-GAE, showcasing it as an independent plug-and-play purifier for GNN classifiers. Our code can be found in https://github.com/woodavid31/GPR-GAE.

This paper addresses the challenge of discontinuity in goal-achievement capabilities observed in Goal-conditioned Reinforcement Learning (GCRL) algorithms. Through a theoretical analysis, we identify that the reuse of successful trajectories or policies during training can aid in achieving adjacent goals of achievable goals. However, the policy discrepancy between achievable and adjacent goals must be carefully managed to avoid both overly trivial and excessively large differences, which can respectively hinder policy performance. To tackle this issue, we propose a margin-based policy self-regularization approach that optimizes the policy discrepancies between adjacent desired goals to a minimal acceptable threshold. This method can be integrated into popular GCRL algorithms, such as GC-SAC, HER, and GC-PPO. Systematic evaluations across two robotic arm control tasks and a complex fixed-wing aircraft control task demonstrate that our approach significantly improves the continuity of goal-achievement abilities of GCRL algorithms, thereby enhancing their overall performance.

We present a principled and simplified design of the projector and loss function for non-contrastive self-supervised learning based on hyperdimensional computing. We theoretically demonstrate that this design introduces an inductive bias that encourages representations to be simultaneously decorrelated and clustered, without explicitly enforcing these properties. This bias provably enhances generalization and suffices to avoid known training failure modes, such as representation, dimensional, cluster, and intracluster collapses. We validate our theoretical findings on image datasets, including SVHN, CIFAR-10, CIFAR-100, and ImageNet-100. Our approach effectively combines the strengths of feature decorrelation and cluster-based self-supervised learning methods, overcoming training failure modes while achieving strong generalization in clustering and linear classification tasks.

Modern semi-supervised learning (SSL) methods rely on pseudolabeling and consistency regularization. Pseudolabeling is typically performed by comparing the model's confidence scores and a predefined threshold. While several heuristics have been proposed to improve threshold selection, the underlying issues of overconfidence and miscalibration in confidence scores remain largely unaddressed, leading to inaccurate pseudolabels, degraded test accuracy, and prolonged training. We take a first-principles approach to learn confidence scores and thresholds with an explicit knob for error. This flexible framework addresses the fundamental question of optimal scores and threshold selection in pseudolabeling. Moreover, it gives practitioners a principled way to control the quality and quantity of pseudolabels. Such control is vital in SSL, where balancing pseudolabel quality and quantity directly affects model performance and training efficiency. Our experiments show that, by integrating this framework with modern SSL methods, we achieve significant improvements in accuracy and training efficiency. In addition, we provide novel insights on the trade-offs between the choices of the error parameter and the end model's performance.

Self-supervised learning has garnered increasing attention in time series analysis for benefiting various downstream tasks and reducing reliance on labeled data. Despite its effectiveness, existing methods often struggle to comprehensively capture both long-term dynamic evolution and subtle local patterns in a unified manner. In this work, we propose \textbf{TimeDART}, a novel self-supervised time series pre-training framework that unifies two powerful generative paradigms to learn more transferable representations. Specifically, we first employ a causal Transformer encoder, accompanied by a patch-based embedding strategy, to model the evolving trends from left to right. Building on this global modeling, we further introduce a denoising diffusion process to capture fine-grained local patterns through forward diffusion and reverse denoising. Finally, we optimize the model in an autoregressive manner. As a result, TimeDART effectively accounts for both global and local sequence features in a coherent way.We conduct extensive experiments on public datasets for time series forecasting and classification. The experimental results demonstrate that TimeDART consistently outperforms previous compared methods, validating the effectiveness of our approach.Our code is available at \url{https://github.com/Melmaphother/TimeDART}.

This paper proposes a scalable and straightforward pre-training paradigm for efficient visual conceptual representation called occluded image contrastive learning (OCL). Our OCL approach is simple: we randomly mask patches to generate different views within an image and contrast them among a mini-batch of images. The core idea behind OCL consists of two designs. First, masked tokens have the potential to significantly diminish the conceptual redundancy inherent in images, and create distinct views with substantial fine-grained differences on the semantic concept level instead of the instance level. Second, contrastive learning is adept at extracting high-level semantic conceptual features during the pre-training, circumventing the high-frequency interference and additional costs associated with image reconstruction. Importantly, OCL learns highly semantic conceptual representations efficiently without relying on hand-crafted data augmentations or additional auxiliary modules. Empirically, OCL demonstrates high scalability with Vision Transformers, as the ViT-L/16 can complete pre-training in 133 hours using only 4 A100 GPUs, achieving 85.8\% accuracy in downstream fine-tuning tasks. Code is available at https://github.com/XiaoyuYoung/OCL.

Recent studies show that in supervised fine-tuning (SFT) of large language models (LLMs), data quality matters more than quantity. While most data cleaning methods concentrate on filtering entire samples, the quality of individual tokens within a sample can vary significantly. After pre-training, even in high-quality samples, patterns or phrases that are not task-related can be redundant, uninformative, or even harmful. Continuing to fine-tune on these patterns may offer limited benefit and even degrade downstream task performance. In this paper, we investigate token quality from a noisy-label perspective and propose a generic token cleaning pipeline for SFT tasks. Our method filters out uninformative tokens while preserving those carrying key task-specific information. Specifically, we first evaluate token quality by examining the influence of model updates on each token, then apply a threshold-based separation. The token influence can be measured in a single pass with a fixed reference model or iteratively with self-evolving reference models. The benefits and limitations of both methods are analyzed theoretically by error upper bounds. Extensive experiments show that our framework consistently improves downstream performance. Code is available at https://github.com/UCSC-REAL/TokenCleaning.

DINO and DINOv2 are two model families being widely used to learn representations from unlabeled imagery data at large scales. Their learned representations often enable state-of-the-art performance for downstream tasks, such as image classification and segmentation. However, they employ many empirically motivated design choices and their training pipelines are highly complex and unstable --- many hyperparameters need to be carefully tuned to ensure that the representations do not collapse --- which poses considerable difficulty to improving them or adapting them to new domains. In this work, we posit that we can remove most such-motivated idiosyncrasies in the pre-training pipelines, and only need to add an explicit coding rate term in the loss function to avoid collapse of the representations. As a result, we obtain highly simplified variants of the DINO and DINOv2 which we call SimDINO and SimDINOv2, respectively. Remarkably, these simplified models are more robust to different design choices, such as network architecture and hyperparameters, and they learn even higher-quality representations, measured by performance on downstream tasks, offering a Pareto improvement over the corresponding DINO and DINOv2 models. This work highlights the potential of using simplifying design principles to improve the empirical practice of deep learning. Code and model checkpoints are available at https://github.com/RobinWu218/SimDINO.

Collecting gold-standard phenotype data via manual extraction is typically labor-intensive and slow, whereas automated computational phenotypes (ACPs) offer a systematic and much faster alternative. However, simply replacing the gold-standard with ACPs, without acknowledging their differences, could lead to biased results and misleading conclusions. Motivated by the complexity of incorporating ACPs while maintaining the validity of downstream analyses, in this paper, we consider a semi-supervised learning setting that consists of both labeled data (with gold-standard) and unlabeled data (without gold-standard), under the covariate shift framework. We develop doubly robust and semiparametrically efficient estimators that leverage ACPs for general target parameters in the unlabeled and combined populations. In addition, we carefully analyze the efficiency gains achieved by incorporating ACPs, comparing scenarios with and without their inclusion. Notably, we identify that ACPs for the unlabeled data, instead of for the labeled data, drive the enhanced efficiency gains. To validate our theoretical findings, we conduct comprehensive synthetic experiments and apply our method to multiple real-world datasets, confirming the practical advantages of our approach.

We introduce SelfCite, a novel self-supervised approach that aligns LLMs to generate high-quality, fine-grained, sentence-level citations for the statements in their generated responses. Instead of only relying on costly and labor-intensive annotations, SelfCite leverages a reward signal provided by the LLM itself through *context ablation*: If a citation is necessary, removing the cited text from the context should prevent the same response; if sufficient, retaining the cited text alone should preserve the same response. This reward can guide the inference-time best-of-N sampling strategy to improve citation quality significantly, as well as be used in preference optimization to directly fine-tune the models for generating better citations. The effectiveness of SelfCite is demonstrated by increasing citation F1 up to 5.3 points on the LongBench-Cite benchmark across five long-form question answering tasks. The source code is available at https://github.com/facebookresearch/SelfCite.

Deep neural networks often develop spurious bias, reliance on correlations between non-essential features and classes for predictions. For example, a model may identify objects based on frequently co-occurring backgrounds rather than intrinsic features, resulting in degraded performance on data lacking these correlations. Existing mitigation approaches typically depend on external annotations of spurious correlations, which may be difficult to obtain and are not relevant to the spurious bias in a model. In this paper, we take a step towards self-guided mitigation of spurious bias by proposing NeuronTune, a post hoc method that directly intervenes in a model's internal decision process. Our method probes in a model's latent embedding space to identify and regulate neurons that lead to spurious prediction behaviors. We theoretically justify our approach and show that it brings the model closer to an unbiased one. Unlike previous methods, NeuronTune operates without requiring spurious correlation annotations, making it a practical and effective tool for improving model robustness. Experiments across different architectures and data modalities demonstrate that our method significantly mitigates spurious bias in a self-guided way.

A growing body of computational studies shows that simple machine learning agents converge to cooperative behaviors in social dilemmas, such as collusive price-setting in oligopoly markets, raising questions about what drives this outcome. In this work, we provide theoretical foundations for this phenomenon in the context of self-play multi-agent Q-learners in the iterated prisoner’s dilemma. We characterize broad conditions under which such agents provably learn the cooperative Pavlov (win-stay, lose-shift) policy rather than the Pareto-dominated “always defect” policy. We validate our theoretical results through additional experiments, demonstrating their robustness across a broader class of deep learning algorithms.

We employ a game-theoretic framework to study the impact of a specific strategic behavior among creators---group behavior---on recommendation platforms. In this setting, creators within a group collaborate to maximize their collective utility. We show that group behavior has a limited effect on the game's equilibrium when the group size is small. However, when the group size is large, group behavior can significantly alter content distribution and user welfare. Specifically, in a top-$K$ recommendation system with exposure-based rewards, we demonstrate that user welfare can suffer a significant loss due to group strategies, and user welfare does not necessarily increase with larger values of $K$ or more random matching, contrasting sharply with the individual creator case. Furthermore, we investigate user welfare guarantees through the lens of the Price of Anarchy (PoA). In the general case, we establish a negative result on the bound of PoA with exposure rewards, proving that it can be arbitrarily large. We then investigate a user engagement rewarding mechanism, which mitigates the issues caused by large group behavior, showing that $\text{PoA}\leq K+1$ in the general case and $\text{PoA}\leq 2$ in the binary case. Empirical results from simulations further support the effectiveness of the user engagement rewarding mechanism.

Garment manipulation is a significant challenge for robots due to the complex dynamics and potential self-occlusion of garments. Most existing methods of efficient garment unfolding overlook the crucial role of standardization of flattened garments, which could significantly simplify downstream tasks like folding, ironing, and packing. This paper presents APS-Net, a novel approach to garment manipulation that combines unfolding and standardization in a unified framework. APS-Net employs a dual-arm, multi-primitive policy with dynamic fling to quickly unfold crumpled garments and pick-and-place(p&p) for precise alignment. The purpose of garment standardization during unfolding involves not only maximizing surface coverage but also aligning the garment’s shape and orientation to predefined requirements. To guide effective robot learning, we introduce a novel factorized reward function for standardization, which incorporates garment coverage (Cov), keypoint distance (KD), and intersection-over-union (IoU) metrics. Additionally, we introduce a spatial action mask and an Action Optimized Module to improve unfolding efficiency by selecting actions and operation points effectively. In simulation, APS-Net outperforms state-of-the-art methods for long sleeves, achieving 3.9% better coverage, 5.2% higher IoU, and a 0.14 decrease in KD (7.09% relative reduction). Real-world folding tasks further demonstrate that standardization simplifies the folding process. Project page: https://hellohaia.github.io/APS/

The past few years have seen remarkable progress in the decoding of speech from brain activity, primarily driven by large single-subject datasets. However, due to individual variation, such as anatomy, and differences in task design and scanning hardware, leveraging data across subjects and datasets remains challenging. In turn, the field has not benefited from the growing number of open neural data repositories to exploit large-scale deep learning. To address this, we develop neuroscience-informed self-supervised objectives, together with an architecture, for learning from heterogeneous brain recordings. Scaling to nearly **400 hours** of MEG data and **900 subjects**, our approach shows generalisation across participants, datasets, tasks, and even to *novel* subjects. It achieves **improvements of 15-27%** over state-of-the-art models and **matches *surgical* decoding performance with *non-invasive* data**. These advances unlock the potential for scaling speech decoding models beyond the current frontier.

Self-Explainable Graph Neural Networks (SE-GNNs) are popular explainable-by-design GNNs, but their explanations' properties and limitations are not well understood. Our first contribution fills this gap by formalizing the explanations extracted by some popular SE-GNNs, referred to as Minimal Explanations (MEs), and comparing them to established notions of explanations, namely Prime Implicant (PI) and faithful explanations. Our analysis reveals that MEs match PI explanations for a restricted but significant family of tasks. In general, however, they can be less informative than PI explanations and are surprisingly misaligned with widely accepted notions of faithfulness. Although faithful and PI explanations are informative, they are intractable to find and we show that they can be prohibitively large. Given these observations, a natural choice is to augment SE-GNNs with alternative modalities of explanations taking care of SE-GNNs’ limitations. To this end, we propose Dual-Channel GNNs that integrate a white-box rule extractor and a standard SE-GNN, adaptively combining both channels. Our experiments show that even a simple instantiation of Dual-Channel GNNs can recover succinct rules and perform on par or better than widely used SE-GNNs.

Diffusion probabilistic models (DPMs) have recently demonstrated impressive generative capabilities. There is emerging evidence that their sample reconstruction ability can yield meaningful representations for recognition tasks. In this paper, we demonstrate that the objectives underlying generation and representation learning are not perfectly aligned. Through a spectral analysis, we find that minimizing the mean squared error (MSE) between the original graph and its reconstructed counterpart does not necessarily optimize representations for downstream tasks. Instead, focusing on reconstructing a small subset of features, specifically those capturing global information, proves to be more effective for learning powerful representations. Motivated by these insights, we propose a novel framework, the Smooth Diffusion Model for Graphs (SDMG), which introduces a multi-scale smoothing loss and low-frequency information encoders to promote the recovery of global, low-frequency details, while suppressing irrelevant high-frequency noise. Extensive experiments validate the effectiveness of our method, suggesting a promising direction for advancing diffusion models in graph representation learning.

Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in LLMs. Interestingly, we observe that both CoT reasoning and self-training share the core objective: iteratively leveraging model-generated information to progressively reduce prediction uncertainty. Building on this insight, we propose a novel CoT framework to improve reasoning performance. Our framework integrates two key components: (i) a task-specific prompt module that optimizes the initial reasoning process, and (ii) an adaptive reasoning iteration module that dynamically refines the reasoning process and addresses the limitations of previous CoT approaches, i.e., over-reasoning and high similarity between consecutive reasoning iterations. Extensive experiments show that the proposed method achieves significant advantages in both performance and computational efficiency. Our code is available at: https://github.com/zongqianwu/ST-COT.

Contrastive Representation Learning (CRL) has achieved impressive success in various domains in recent years. Nevertheless, the theoretical understanding of the generalization behavior of CRL has remained limited. Moreover, to the best of our knowledge, the current literature only analyzes generalization bounds under the assumption that the data tuples used for contrastive learning are independently and identically distributed. However, in practice, we are often limited to a fixed pool of reusable labeled data points, making it inevitable to recycle data across tuples to create sufficiently large datasets. Therefore, the tuple-wise independence condition imposed by previous works is invalidated. In this paper, we provide a generalization analysis for the CRL framework under non-$i.i.d.$ settings that adheres to practice more realistically. Drawing inspiration from the literature on U-statistics, we derive generalization bounds which indicate that the required number of samples in each class scales as the logarithm of the covering number of the class of learnable feature representations associated to that class. Next, we apply our main results to derive excess risk bounds for common function classes such as linear maps and neural networks.