ICML 2024 论文列表

The analysis of scientific data and complex multivariate systems requires information quantities that capture relationships among multiple random variables. Recently, new information-theoretic measures have been developed to overcome the shortcomings of classical ones, such as mutual information, that are restricted to considering pairwise interactions. Among them, the concept of information synergy and redundancy is crucial for understanding the high-order dependencies between variables. One of the most prominent and versatile measures based on this concept is *O-information*, which provides a clear and scalable way to quantify the synergy-redundancy balance in multivariate systems. However, its practical application is limited to simplified cases. In this work, we introduce **S$\Omega$I**, which allows to compute *O-information* without restrictive assumptions about the system while leveraging a unique model. Our experiments validate our approach on synthetic data, and demonstrate the effectiveness of **S$\Omega$I** in the context of a real-world use case.

Modern information retrieval (IR) systems consists of multiple stages like retrieval and ranking, with Transformer-based models achieving state-of-the-art performance at each stage. In this paper, we challenge the tradition of using separate models for different stages and ask if a single Transformer encoder can provide relevance score needed in each stage. We present USTAD – a new unified approach to train a single network that can provide powerful ranking scores as a cross-encoder (CE) model as well as factorized embeddings for large-scale retrieval as a dual-encoder (DE) model. Empirically, we find a single USTAD model to be competitive to separate ranking CE and retrieval DE models. Furthermore, USTAD combines well with a novel embedding matching-based distillation, significantly improving CE to DE distillation. It further motivates novel asymmetric architectures for student models to ensure a better embedding alignment between the student and the teacher while ensuring small online inference cost. On standard benchmarks like MSMARCO, we demonstrate that USTAD with our proposed distillation method leads to asymmetric students with only 1/10th trainable parameter but retaining 95-97% of the teacher performance.

It is known that when the statistical models are singular, i.e., the Fisher information matrix at the true parameter is degenerate, the fixed step-size gradient descent algorithm takes polynomial number of steps in terms of the sample size $n$ to converge to a final statistical radius around the true parameter, which can be unsatisfactory for the practical application. To further improve that computational complexity, we consider utilizing the local curvature information for parameter estimation. Even though there is a rich literature in using the local curvature information for optimization, the statistical rate of these methods in statistical models, to the best of our knowledge, has not been studied rigorously. The major challenge of this problem is due to the non-convex nature of sample loss function. To shed light on these problems, we specifically study the normalized gradient descent (NormGD) algorithm, a variant of gradient descent algorithm whose step size is scaled by the maximum eigenvalue of the Hessian matrix of the empirical loss function, and deal with the aforementioned issue with a population-to-sample analysis. When the population loss function is homogeneous, the NormGD iterates reach a final statistical radius around the true parameter after a logarithmic number of iterations in terms of $n$. Therefore, for fixed dimension $d$, the NormGD algorithm achieves the optimal computational complexity $\mathcal{O}(n)$ to reach the final statistical radius, which is cheaper than the complexity $\mathcal{O}(n^{\tau})$ of the fixed step-size gradient descent algorithm for some $\tau > 1$.

Exploiting invariant relations and mitigating spurious correlation (a.k.a., shortcut) between representation and target across varied data distributions can tackle the challenging out-of-distribution (OOD) generalization problem. In personalized federated learning (PFL), heterogeneous data distribution across local clients offers the inherent prerequisites to extract the invariant features that maintain invariant relation with target. Nevertheless, personalized features are closely entangled with spurious features in PFL since they exhibit similar variability across different clients, which makes preserving personalization knowledge and eliminating shortcuts two conflicting objectives in PFL. To address the above challenge, we analyse the heterogeneous data generation on local clients through the lens of structured causal model and propose a crucial causal signature which can distinguish personalized features from spurious features with global invariant features as the anchor. Then the causal signature is quantified as an information-theoretic constraint that facilitates the shortcut-averse personalized invariant learning on each client. Theoretical analysis demonstrates our method, FedPIN, can yield a tighter bound on generalization error than the prevalent PFL approaches when train-test distribution shift exists on clients. Moreover, we provide a theoretical guarantee on the convergence rate of FedPIN in this paper. The results of extensive experiments show that our method can achieve superior OOD generalization performance compared with the state-of-the-art competitors.

Opponent exploitation is an important task for players to exploit the weaknesses of others in games. Existing approaches mainly focus on balancing between exploitation and exploitability but are often vulnerable to modeling errors and deceptive adversaries. To address this problem, our paper offers a novel perspective on the safety of opponent exploitation, named Adaptation Safety. This concept leverages the insight that strategies, even those not explicitly aimed at opponent exploitation, may inherently be exploitable due to computational complexities, rendering traditional safety overly rigorous. In contrast, adaptation safety requires that the strategy should not be more exploitable than it would be in scenarios where opponent exploitation is not considered. Building on such adaptation safety, we further propose an Opponent eXploitation Search (OX-Search) framework by incorporating real-time search techniques for efficient online opponent exploitation. Moreover, we provide theoretical analyses to show the adaptation safety and robust exploitation of OX-Search, even with inaccurate opponent models. Empirical evaluations in popular poker games demonstrate OX-Search's superiority in both exploitability and exploitation compared to previous methods.

Policy optimization from batch data, i.e., offline reinforcement learning (RL) is important when collecting data from a current policy is not possible. This setting incurs distribution mismatch between batch training data and trajectories from the current policy. Pessimistic offsets estimate mismatch using concentration bounds, which possess strong theoretical guarantees and simplicity of implementation. Mismatch may be conservative in sparse data regions and less so otherwise, which can result in under-performing their no-penalty variants in practice. We derive a new pessimistic penalty as the distance between the data and the true distribution using an evaluable one-sample test known as Stein Discrepancy that requires minimal smoothness conditions, and noticeably, allows a mixture family representation of distribution over next states. This entity forms a quantifier of information in offline data, which justifies calling this approach *information-directed pessimism* (IDP) for offline RL. We further establish that this new penalty based on discrete Stein discrepancy yields practical gains in performance while generalizing the regret of prior art to multimodal distributions.

The Weisfeiler--Leman algorithm (1-WL) is a well-studied heuristic for the graph isomorphism problem. Recently, the algorithm has played a prominent role in understanding the expressive power of message-passing graph neural networks (MPNNs) and being effective as a graph kernel. Despite its success, the 1-WL faces challenges in distinguishing non-isomorphic graphs, leading to the development of more expressive MPNN and kernel architectures. However, the relationship between enhanced expressivity and improved generalization performance remains unclear. Here, we show that an architecture's expressivity offers limited insights into its generalization performance when viewed through graph isomorphism. Moreover, we focus on augmenting 1-WL and MPNNs with subgraph information and employ classical margin theory to investigate the conditions under which an architecture's increased expressivity aligns with improved generalization performance. In addition, we introduce variations of expressive 1-WL-based kernel and MPNN architectures with provable generalization properties. Our empirical study confirms the validity of our theoretical findings.

Generative models inspired by dynamical transport of measure -- such as flows and diffusions -- construct a continuous-time map between two probability densities. Conventionally, one of these is the target density, only accessible through samples, while the other is taken as a simple base density that is data-agnostic. In this work, using the framework of stochastic interpolants, we formalize how to *couple* the base and the target densities, whereby samples from the base are computed conditionally given samples from the target in a way that is different from (but does not preclude) incorporating information about class labels or continuous embeddings. This enables us to construct dynamical transport maps that serve as conditional generative models. We show that these transport maps can be learned by solving a simple square loss regression problem analogous to the standard independent setting. We demonstrate the usefulness of constructing dependent couplings in practice through experiments in super-resolution and in-painting. The code is available at [https://github.com/interpolants/couplings](https://github.com/interpolants/couplings).

Deep Neural Networks (DNN) have shown great promise in many classification applications, yet are widely known to have poorly calibrated predictions when they are over-parametrized. Improving DNN calibration without comprising on model accuracy is of extreme importance and interest in safety critical applications such as in the health-care sector. In this work, we show that decoupling the training of feature extraction layers and classification layers in over-parametrized DNN architectures such as Wide Residual Networks (WRN) and Vision Transformers (ViT) significantly improves model calibration whilst retaining accuracy, and at a low training cost. In addition, we show that placing a Gaussian prior on the last hidden layer outputs of a DNN, and training the model variationally in the classification training stage, even further improves calibration. We illustrate these methods improve calibration across ViT and WRN architectures for several image classification benchmark datasets.

Model extraction is to obtain a cloned model that replicates the functionality of a black-box victim model solely through query-based access. Present defense strategies exhibit shortcomings, manifesting as: (1) computational or memory inefficiencies during deployment; or (2) dependence on expensive defensive training methods that mandate the re-training of the victim model; or (3) watermarking-based methods only *passively* detect model theft without actively preventing model extraction. To address these limitations, we introduce an innovative Bayesian *active* watermarking technique to fine-tune the victim model and learn the watermark posterior distribution conditioned on input data. The fine-tuning process aims to maximize the log-likelihood on watermarked in-distribution training data for preserving model utility while simultaneously maximizing the change of model's outputs on watermarked out-of-distribution data, thereby achieving effective defense. During deployment, a watermark is randomly sampled from the estimated watermark posterior. This watermark is then added to the input query, and the victim model returns the prediction based on the watermarked input query to users. This proactive defense approach requires only slight fine-tuning of the victim model without the need of full re-training and demonstrates high efficiency in terms of memory and computation during deployment. Rigorous theoretical analysis and comprehensive experimental results demonstrate the efficacy of our proposed method.

Both the marginal contributions needed for the computation of Shapley values and the graph produced by Pearl-Verma theorem rely on the choice of an ordering of the variables. For Shapley values, the marginal contributions are averaged over all orderings, while in causal inference methods, the typical approach is to select orderings producing a graph with a minimal number of edges. We reconcile both approaches by reinterpreting them from a maximum entropy perspective. Namely, Shapley values assume no prior knowledge about the orderings and treat them as equally likely, while causal inference approaches apply Occam's razor and consider only orderings producing the simplest explanatory graphs. We find that the blind application of Occam's razor to Shapley values does not produce fully satisfactory explanations. Hence, we propose two variations of Shapley values based on entropy maximization to appropriately incorporate prior information about the model. Hence, we propose a variation of Shapley values based on entropy maximization to appropriately incorporate prior information about the model.

Model merging and task arithmetic have emerged as promising scalable approaches to merge multiple single-task checkpoints to one multi-task model, but their applicability is reduced by significant performance loss. Previous works have linked these drops to interference in the weight space and erasure of important task-specific features. Instead, in this work we show that the information required to solve each task is still preserved after merging as different tasks mostly use non-overlapping sets of weights. We propose TALL-masks, a method to identify these task supports given a collection of task vectors and show that one can retrieve >99% of the single task accuracy by applying our masks to the multi-task vector, effectively compressing the individual checkpoints. We study the statistics of intersections among constructed masks and reveal the existence of selfish and catastrophic weights, i.e., parameters that are important exclusively to one task and irrelevant to all tasks but detrimental to multi-task fusion. For this reason, we propose Consensus Merging, an algorithm that eliminates such weights and improves the general performance of existing model merging approaches. Our experiments in vision and NLP benchmarks with up to 20 tasks, show that Consensus Merging consistently improves existing approaches. Furthermore, our proposed compression scheme reduces storage from 57Gb to 8.2Gb while retaining 99.7% of original performance.

Despite the success of the carefully-annotated benchmarks, the effectiveness of existing graph neural networks (GNNs) can be considerably impaired in practice when the real-world graph data is noisily labeled. Previous explorations in sample selection have been demonstrated as an effective way for robust learning with noisy labels, however, the conventional studies focus on i.i.d data, and when moving to non-iid graph data and GNNs, two notable challenges remain: (1) nodes located near topological class boundaries are very informative for classification but cannot be successfully distinguished by the heuristic sample selection. (2) there is no available measure that considers the graph topological information to promote sample selection in a graph. To address this dilemma, we propose a $\textit{Topological Sample Selection}$ (TSS) method that boosts the informative sample selection process in a graph by utilising topological information. We theoretically prove that our procedure minimizes an upper bound of the expected risk under target clean distribution, and experimentally show the superiority of our method compared with state-of-the-art baselines.

One of the fundamental representation learning tasks is unsupervised sequential disentanglement, where latent codes of inputs are decomposed to a single static factor and a sequence of dynamic factors. To extract this latent information, existing methods condition the static and dynamic codes on the entire input sequence. Unfortunately, these models often suffer from information leakage, i.e., the dynamic vectors encode both static and dynamic information, or vice versa, leading to a non-disentangled representation. Attempts to alleviate this problem via reducing the dynamic dimension and auxiliary loss terms gain only partial success. Instead, we propose a novel and simple architecture that mitigates information leakage by offering a simple and effective subtraction inductive bias while conditioning on a single sample. Remarkably, the resulting variational framework is simpler in terms of required loss terms, hyper-parameters, and data augmentation. We evaluate our method on multiple data-modality benchmarks including general time series, video, and audio, and we show beyond state-of-the-art results on generation and prediction tasks in comparison to several strong baselines.

Knowledge Graphs (KGs) are potent frameworks for knowledge representation and reasoning. Nevertheless, KGs are inherently incomplete, leaving numerous uncharted relationships and facts awaiting discovery. Deep learning methodologies have proven effective in enhancing KG completion by framing it as a link prediction task, where the goal is to discern the validity of a triple comprising a head, relation, and tail. The significance of structural information in assessing the validity of a triple within a KG is well-established. However, quantifying this structural information poses a challenge. We need to pinpoint the metric that encapsulates the structural information of a triple and smoothly incorporate this metric into the link prediction learning process. In this study, we recognize the critical importance of the intersection among the $k$-hop neighborhoods of the head, relation, and tail when determining the validity of a triple. To address this, we introduce a novel randomized algorithm designed to efficiently generate intersection features for candidate triples. Our experimental results demonstrate that a straightforward fully-connected network leveraging these intersection features can surpass the performance of established KG embedding models and even outperform graph neural network baselines. Additionally, we highlight the substantial training time efficiency gains achieved by our network trained on intersection features.

Label noise is a pervasive problem in deep learning that often compromises the generalization performance of trained models. Recently, leveraging privileged information (PI) -- information available only during training but not at test time -- has emerged as an effective approach to mitigate this issue. Yet, existing PI-based methods have failed to consistently outperform their no-PI counterparts in terms of preventing overfitting to label noise. To address this deficiency, we introduce Pi-DUAL, an architecture designed to harness PI to distinguish clean from wrong labels. Pi-DUAL decomposes the output logits into a prediction term, based on conventional input features, and a noise-fitting term influenced solely by PI. A gating mechanism steered by PI adaptively shifts focus between these terms, allowing the model to implicitly separate the learning paths of clean and wrong labels. Empirically, Pi-DUAL achieves significant performance improvements on key PI benchmarks (e.g., +6.8% on ImageNet-PI), establishing a new state-of-the-art test set accuracy. Additionally, Pi-DUAL is a potent method for identifying noisy samples post-training, outperforming other strong methods at this task. Overall, Pi-DUAL is a simple, scalable and practical approach for mitigating the effects of label noise in a variety of real-world scenarios with PI.

Neural networks extract features from data using stochastic gradient descent (SGD). In particular, higher-order input cumulants (HOCs) are crucial for their performance. However, extracting information from the $p$th cumulant of $d$-dimensional inputs is computationally hard: the number of samples required to recover a single direction from an order-$p$ tensor (tensor PCA) using SGD grows as $d^{p−1}$, which is prohibitive for high-dimensional inputs. This result raises the question of how neural networks extract relevant directions from the HOCs of their inputs efficiently. Here, we show that correlations between latent variables along the directions encoded in different input cumulants speed up learning from higher-order correlations. We show this effect analytically by deriving nearly sharp thresholds for the number of samples required by a single neuron to recover these directions using online SGD from a random start in high dimensions. Our analytical results are confirmed in simulations of two-layer neural networks and unveil a new mechanism for hierarchical learning in neural networks

Medical vision-language pre-training methods mainly leverage the correspondence between paired medical images and radiological reports. Although multi-view spatial images and temporal sequences of image-report pairs are available in off-the-shelf multi-modal medical datasets, most existing methods have not thoroughly tapped into such extensive supervision signals. In this paper, we introduce the Med-ST framework for fine-grained spatial and temporal modeling to exploit information from multiple spatial views of chest radiographs and temporal historical records. For spatial modeling, Med-ST employs the *Mixture of View Expert (MoVE)* architecture to integrate different visual features from both frontal and lateral views. To achieve a more comprehensive alignment, Med-ST not only establishes the global alignment between whole images and texts but also introduces modality-weighted local alignment between text tokens and spatial regions of images. For temporal modeling, we propose a novel cross-modal bidirectional cycle consistency objective by forward mapping classification (FMC) and reverse mapping regression (RMR). By perceiving temporal information from simple to complex, Med-ST can learn temporal semantics. Experimental results across four distinct tasks demonstrate the effectiveness of Med-ST, especially in temporal classification tasks. Our code and model are available at https://github.com/SVT-Yang/MedST.

The growing richness of large-scale datasets has been crucial in driving the rapid advancement and wide adoption of machine learning technologies. The massive collection and usage of data, however, pose an increasing risk for people's private and sensitive information due to either inadvertent mishandling or malicious exploitation. Besides legislative solutions, many technical approaches have been proposed towards data privacy protection. However, they bear various limitations such as leading to degraded data availability and utility, or relying on heuristics and lacking solid theoretical bases. To overcome these limitations, we propose a formal information-theoretic definition for this utility-preserving privacy protection problem, and design a data-driven learnable data transformation framework that is capable of selectively suppressing sensitive attributes from target datasets while preserving the other useful attributes, regardless of whether or not they are known in advance or explicitly annotated for preservation. We provide rigorous theoretical analyses on the operational bounds for our framework, and carry out comprehensive experimental evaluations using datasets of a variety of modalities, including facial images, voice audio clips, and human activity motion sensor signals. Results demonstrate the effectiveness and generalizability of our method under various configurations on a multitude of tasks. Our source code is available at this [URL](https://arxiv.org/abs/2405.14981).