Information Extraction

Empirical Risk Minimization (ERM) is fragile in scenarios with insufficient labeled samples. A vanilla extension of ERM to unlabeled samples is Entropy Minimization (EntMin), which employs the soft-labels of unlabeled samples to guide their learning. However, EntMin emphasizes prediction discriminability while neglecting prediction diversity. To alleviate this issue, in this paper, we rethink the guidance information to utilize unlabeled samples. By analyzing the learning objective of ERM, we find that the guidance information for labeled samples in a specific category is the corresponding *label encoding*. Inspired by this finding, we propose a Label-Encoding Risk Minimization (LERM). It first estimates the label encodings through prediction means of unlabeled samples and then aligns them with their corresponding ground-truth label encodings. As a result, the LERM ensures both prediction discriminability and diversity, and it can be integrated into existing methods as a plugin. Theoretically, we analyze the relationships between LERM and ERM as well as EntMin. Empirically, we verify the superiority of the LERM under several label insufficient scenarios. The codes are available at https://github.com/zhangyl660/LERM.

The recent surge in contrastive learning has intensified the interest in understanding the generalization of non-pointwise learning paradigms. While information-theoretic analysis achieves remarkable success in characterizing the generalization behavior of learning algorithms, its applicability is largely confined to pointwise learning, with extensions to the simplest pairwise settings remaining unexplored due to the challenges of non-i.i.d losses and dimensionality explosion. In this paper, we develop the first series of information-theoretic bounds extending beyond pointwise scenarios, encompassing pointwise, pairwise, triplet, quadruplet, and higher-order scenarios, all within a unified framework. Specifically, our hypothesis-based bounds elucidate the generalization behavior of iterative and noisy learning algorithms via gradient covariance analysis, and our prediction-based bounds accurately estimate the generalization gap with computationally tractable low-dimensional information metrics. Comprehensive numerical studies then demonstrate the effectiveness of our bounds in capturing the generalization dynamics across diverse learning scenarios.

In many applications like experimental design, group testing, and medical diagnosis, the state of a random variable $Y$ is revealed by successively observing the outcomes of binary tests about $Y$. New tests are selected adaptively based on the history of outcomes observed so far. If the number of states of $Y$ is finite, the process ends when $Y$ can be predicted with a desired level of confidence or all available tests have been used. Finding the strategy that minimizes the expected number of tests needed to predict $Y$ is virtually impossible in most real applications. Therefore, the commonly used strategy is the greedy heuristic of Information Maximization (InfoMax) that selects tests sequentially in order of information gain. Despite its widespread use, existing guarantees on its performance are often vacuous when compared to its empirical efficiency. In this paper, for the first time to the best of our knowledge, we establish tight non-vacuous bounds on InfoMax's performance. Our analysis is based on the assumption that at any iteration of the greedy strategy, there is always a binary test available whose conditional probability of being 'true', given the history, is within $\delta$ units of one-half. This assumption is motivated by practical applications where the available set of tests often satisfies this property for modest values of $\delta$, say, ${0.1 \leq \delta \leq 0.4}$. Specifically, we analyze two distinct scenarios: (i) all tests are functions of $Y$, and (ii) test outcomes are corrupted by a binary symmetric channel. For both cases, our bounds guarantee the near-optimal performance of InfoMax for modest $\delta$ values. It requires only a small multiplicative factor of the entropy of $Y$, in terms of the average number of tests needed to make accurate predictions.

The maximum entropy encoding framework provides a unified perspective for many non-contrastive learning methods like SimSiam, Barlow Twins, and MEC. Inspired by this framework, we introduce Matrix-SSL, a novel approach that leverages matrix information theory to interpret the maximum entropy encoding loss as matrix uniformity loss. Furthermore, Matrix-SSL enhances the maximum entropy encoding method by seamlessly incorporating matrix alignment loss, directly aligning covariance matrices in different branches. Experimental results reveal that Matrix-SSL outperforms state-of-the-art methods on the ImageNet dataset under linear evaluation settings and on MS-COCO for transfer learning tasks. Specifically, when performing transfer learning tasks on MS-COCO, our method outperforms previous SOTA methods such as MoCo v2 and BYOL up to 3.3% with only 400 epochs compared to 800 epochs pre-training. We also try to introduce representation learning into the language modeling regime by fine-tuning a 7B model using matrix cross-entropy loss, with a margin of 3.1% on the GSM8K dataset over the standard cross-entropy loss.

In this paper, we conduct a comprehensive analysis of two dual-branch (Siamese architecture) self-supervised learning approaches, namely Barlow Twins and spectral contrastive learning, through the lens of matrix mutual information. We prove that the loss functions of these methods implicitly optimize both matrix mutual information and matrix joint entropy. This insight prompts us to further explore the category of single-branch algorithms, specifically MAE and U-MAE, for which mutual information and joint entropy become the entropy. Building on this intuition, we introduce the Matrix Variational Masked Auto-Encoder (M-MAE), a novel method that leverages the matrix-based estimation of entropy as a regularizer and subsumes U-MAE as a special case. The empirical evaluations underscore the effectiveness of M-MAE compared with the state-of-the-art methods, including a 3.9% improvement in linear probing ViT-Base, and a 1% improvement in fine-tuning ViT-Large, both on ImageNet.

Latent representations are extensively used for tasks like visualization, interpolation, or feature extraction in deep learning models. This paper demonstrates the importance of considering the inductive bias imposed by an equivariant model when using latent representations as neglecting these biases can lead to decreased performance in downstream tasks. We propose principles for choosing invariant projections of latent representations and show their effectiveness in two examples: A permutation equivariant variational auto-encoder for molecular graph generation, where an invariant projection can be designed to maintain information without loss, and for a rotation-equivariant representation in image classification, where random invariant projections proves to retain a high degree of information. In both cases, the analysis of invariant latent representations proves superior to their equivariant counterparts. Finally, we illustrate that the phenomena documented here for equivariant neural networks have counterparts in standard neural networks where invariance is encouraged via augmentation.

The ability of machine learning (ML) algorithms to generalize well to unseen data has been studied through the lens of information theory, by bounding the generalization error with the input-output mutual information (MI), i.e., the MI between the training data and the learned hypothesis. Yet, these bounds have limited practicality for modern ML applications (e.g., deep learning), due to the difficulty of evaluating MI in high dimensions. Motivated by recent findings on the compressibility of neural networks, we consider algorithms that operate by *slicing* the parameter space, i.e., trained on random lower-dimensional subspaces. We introduce new, tighter information-theoretic generalization bounds tailored for such algorithms, demonstrating that slicing improves generalization. Our bounds offer significant computational and statistical advantages over standard MI bounds, as they rely on scalable alternative measures of dependence, i.e., disintegrated mutual information and $k$-sliced mutual information. Then, we extend our analysis to algorithms whose parameters do not need to exactly lie on random subspaces, by leveraging rate-distortion theory. This strategy yields generalization bounds that incorporate a distortion term measuring model compressibility under slicing, thereby tightening existing bounds without compromising performance or requiring model compression. Building on this, we propose a regularization scheme enabling practitioners to control generalization through compressibility. Finally, we empirically validate our results and achieve the computation of non-vacuous information-theoretic generalization bounds for neural networks, a task that was previously out of reach.

Existing few-shot semantic segmentation methods typically rely on a one-way flow of category information from support to query, ignoring the impact of intra-class diversity. To address this, drawing inspiration from cybernetics, we introduce a Query Feedback Branch (QFB) to propagate query information back to support, generating a query-related support prototype that is more aligned with the query. Subsequently, a Query Amplifier Branch (QAB) is employed to amplify target objects in the query using the acquired support prototype. To further improve the model, we propose a Query Rectification Module (QRM), which utilizes the prediction disparity in the query before and after support activation to identify challenging positive and negative samples from ambiguous regions for query self-rectification. Furthermore, we integrate the QFB, QAB, and QRM into a feedback and rectification layer and incorporate it into an iterative pipeline. This configuration enables the progressive enhancement of bidirectional reciprocative flow of category information between query and support, effectively providing query-adaptive support information and addressing the intra-class diversity problem. Extensive experiments conducted on both PASCAL-5i and COCO-20i datasets validate the effectiveness of our approach. The code is available at https://github.com/LIUYUANWEI98/IFRNet .

Explaining deep learning models operating on time series data is crucial in various applications of interest which require interpretable and transparent insights from time series signals. In this work, we investigate this problem from an information theoretic perspective and show that most existing measures of explainability may suffer from trivial solutions and distributional shift issues. To address these issues, we introduce a simple yet practical objective function for time series explainable learning. The design of the objective function builds upon the principle of information bottleneck (IB), and modifies the IB objective function to avoid trivial solutions and distributional shift issues. We further present TimeX++, a novel explanation framework that leverages a parametric network to produce explanation-embedded instances that are both in-distributed and label-preserving. We evaluate TimeX++ on both synthetic and real-world datasets comparing its performance against leading baselines, and validate its practical efficacy through case studies in a real-world environmental application. Quantitative and qualitative evaluations show that TimeX++ outperforms baselines across all datasets, demonstrating a substantial improvement in explanation quality for time series data. The source code is available at https://github.com/zichuan-liu/TimeXplusplus.

Molecular surfaces imply fingerprints of interaction patterns between proteins. However, non-equivalent efforts have been paid to incorporating the abundant protein surface information for analyzing proteins' biological functions in juxtaposition to amino acid sequences and 3D structures. We propose a novel surface-based unsupervised learning algorithm termed Surface-VQMAE to overcome this obstacle. In light of surface point clouds' sparsity and disorder properties, we first partition them into patches and obtain the sequential arrangement via the Morton curve. Successively, a Transformer-based architecture named SurfFormer was introduced to integrate the surface geometry and capture patch-level relations. At last, we enhance the prevalent masked auto-encoder (MAE) with the vector quantization (VQ) technique, which establishes a surface pattern codebook to enforce a discrete posterior distribution of latent variables and achieve more condensed semantics. Our work is the foremost to implement pretraining purely on molecular surfaces and extensive experiments on diverse real-life scenarios including binding site scoring, binding affinity prediction, and mutant effect estimation demonstrate its effectiveness. The code is available at https://github.com/smiles724/VQMAE.

Value iteration networks (VINs) enable end-to-end learning for planning tasks by employing a differentiable "planning module" that approximates the value iteration algorithm. However, long-term planning remains a challenge because training very deep VINs is difficult. To address this problem, we embed highway value iteration---a recent algorithm designed to facilitate long-term credit assignment---into the structure of VINs. This improvement augments the "planning module" of the VIN with three additional components: 1) an "aggregate gate," which constructs skip connections to improve information flow across many layers; 2) an "exploration module," crafted to increase the diversity of information and gradient flow in spatial dimensions; 3) a "filter gate" designed to ensure safe exploration. The resulting novel highway VIN can be trained effectively with hundreds of layers using standard backpropagation. In long-term planning tasks requiring hundreds of planning steps, deep highway VINs outperform both traditional VINs and several advanced, very deep NNs.

The transformer architecture has prevailed in various deep learning settings due to its exceptional capabilities to select and compose structural information. Motivated by these capabilities, Sanford et al. (2023) proposed the *sparse token selection* task, in which transformers excel while fully-connected networks (FCNs) fail in the worst case. Building upon that, we strengthen the FCN lower bound to an average-case setting and establish an algorithmic separation of transformers over FCNs. Specifically, a one-layer transformer trained with gradient descent provably learns the sparse token selection task and, surprisingly, exhibits strong out-of-distribution length generalization. We provide empirical simulations to justify our theoretical findings.

Modern high-stakes systems, such as healthcare or robotics, often generate vast streaming event sequences. Our goal is to design an efficient, plug-and-play tool to elicit logic tree-based explanations from Large Language Models (LLMs) to provide customized insights into each observed event sequence. Built on the temporal point process model for events, our method employs the likelihood function as a score to evaluate generated logic trees. We propose an amortized Expectation-Maximization (EM) learning framework and treat the logic tree as latent variables. In the E-step, we evaluate the posterior distribution over the latent logic trees using an LLM prior and the likelihood of the observed event sequences. LLM provides a high-quality prior for the latent logic trees, however, since the posterior is built over a discrete combinatorial space, we cannot get the closed-form solution. We propose to generate logic tree samples from the posterior using a learnable GFlowNet, which is a diversity-seeking generator for structured discrete variables. The M-step employs the generated logic rules to approximate marginalization over the posterior, facilitating the learning of model parameters and refining the tunable LLM prior parameters. In the online setting, our locally built, lightweight model will iteratively extract the most relevant rules from LLMs for each sequence using only a few iterations. Empirical demonstrations showcase the promising performance and adaptability of our framework.

Effective action abstraction is crucial in tackling challenges associated with large action spaces in Imperfect Information Extensive-Form Games (IIEFGs). However, due to the vast state space and computational complexity in IIEFGs, existing methods often rely on fixed abstractions, resulting in sub-optimal performance. In response, we introduce RL-CFR, a novel reinforcement learning (RL) approach for dynamic action abstraction. RL-CFR builds upon our innovative Markov Decision Process (MDP) formulation, with states corresponding to public information and actions represented as feature vectors indicating specific action abstractions. The reward is defined as the expected payoff difference between the selected and default action abstractions. RL-CFR constructs a game tree with RL-guided action abstractions and utilizes counterfactual regret minimization (CFR) for strategy derivation. Impressively, it can be trained from scratch, achieving higher expected payoff without increased CFR solving time. In experiments on Heads-up No-limit Texas Hold'em, RL-CFR outperforms ReBeL's replication and Slumbot, demonstrating significant win-rate margins of $64\pm 11$ and $84\pm 17$ mbb/hand, respectively.

In many interactive decision-making problems, there is contextual side information that remains fixed within the course of an interaction. This problem has been studied quite extensively under the assumption the context is fully observed, as well as in the opposing limit when the context is unobserved, a special type of POMDP also referred to as a Latent MDP (LMDP). In this work, we consider a class of decision problems that interpolates between the settings, namely, between the case the context is fully observed, and the case the context is unobserved. We refer to this class of decision problems as *LMDPs with prospective side information*. In such an environment an agent receives additional, weakly revealing, information on the latent context at the beginning of each episode. We show that, surprisingly, this problem is not captured by contemporary POMDP settings and is not solved by RL algorithms designed for partially observed environments. We then establish that any sample efficient algorithm must suffer at least $\Omega(K^{2/3})$-regret, as opposed to standard $\Omega(\sqrt{K})$ lower bounds. We design an algorithm with a matching upper bound that depends only polynomially on the problem parameters. This establishes exponential improvement in the sample complexity relative to the existing LMDP lower bound, when prospective information is not given in prior work.

Offline Imitation Learning (IL) with imperfect demonstrations has garnered increasing attention owing to the scarcity of expert data in many real-world domains. A fundamental problem in this scenario is *how to extract positive behaviors from noisy data*. In general, current approaches to the problem select data building on state-action similarity to given expert demonstrations, neglecting precious information in (potentially abundant) *diverse* state-actions that deviate from expert ones. In this paper, we introduce a simple yet effective data selection method that identifies positive behaviors based on their *resultant states* - a more informative criterion enabling explicit utilization of dynamics information and effective extraction of both expert and beneficial diverse behaviors. Further, we devise a lightweight behavior cloning algorithm capable of leveraging the expert and selected data correctly. In the experiments, we evaluate our method on a suite of complex and high-dimensional offline IL benchmarks, including continuous-control and vision-based tasks. The results demonstrate that our method achieves state-of-the-art performance, outperforming existing methods on **20/21** benchmarks, typically by **2-5x**, while maintaining a comparable runtime to Behavior Cloning (BC).

A recent theory shows that a multi-player decentralized partially observable Markov decision process can be transformed into an equivalent single-player game, enabling the application of Bellman's principle of optimality to solve the single-player game by breaking it down into single-stage subgames. However, this approach entangles the decision variables of all players at each single-stage subgame, resulting in backups with a double-exponential complexity. This paper demonstrates how to disentangle these decision variables while maintaining optimality under hierarchical information sharing, a prominent management style in our society. To achieve this, we apply the principle of optimality to solve any single-stage subgame by breaking it down further into smaller subgames, enabling us to make single-player decisions at a time. Our approach reveals that extensive-form games always exist with solutions to a single-stage subgame, significantly reducing time complexity. Our experimental results show that the algorithms leveraging these findings can scale up to much larger multi-player games without compromising optimality.

Reinforcement Learning (RL) from temporal logical specifications is a fundamental problem in sequential decision making. One of the basic and core such specification is the reachability specification that requires a target set to be eventually visited. Despite strong empirical results for RL from such specifications, the theoretical guarantees are bleak, including the impossibility of Probably Approximately Correct (PAC) guarantee for reachability specifications. Given the impossibility result, in this work we consider the problem of RL from reachability specifications along with the information of expected conditional distance (ECD). We present (a) lower bound results which establish the necessity of ECD information for PAC guarantees and (b) an algorithm that establishes PAC-guarantees given the ECD information. To the best of our knowledge, this is the first RL from reachability specifications that does not make any assumptions on the underlying environment to learn policies.

The LoRA-finetuning quantization of LLMs has been extensively studied to obtain accurate yet compact LLMs for deployment on resource-constrained hardware. However, existing methods cause the quantized LLM to severely degrade and even fail to benefit from the finetuning of LoRA. This paper proposes a novel IR-QLoRA for pushing quantized LLMs with LoRA to be highly accurate through information retention. The proposed IR-QLoRA mainly relies on two technologies derived from the perspective of unified information: (1) statistics-based Information Calibration Quantization allows the quantized parameters of LLM to retain original information accurately; (2) finetuning-based Information Elastic Connection makes LoRA utilizes elastic representation transformation with diverse information. Comprehensive experiments show that IR-QLoRA can significantly improve accuracy across LLaMA and LLaMA2 families under 2-4 bit-widths, e.g., 4-bit LLaMA-7B achieves 1.4% improvement on MMLU compared with the state-of-the-art methods. The significant performance gain requires only a tiny 0.31% additional time consumption, revealing the satisfactory efficiency of our IR-QLoRA. We highlight that IR-QLoRA enjoys excellent versatility, compatible with various frameworks (e.g., NormalFloat and Integer quantization) and brings general accuracy gains. The code is available at https://github.com/htqin/ir-qlora .

Self-attention and transformers have been widely used in deep learning. Recent efforts have been devoted to incorporating transformer blocks into different types of neural architectures, including those with convolutions, leading to various visual transformers for computer vision tasks. In this paper, we propose a novel and compact transformer block, Transformer with Differentiable Channel Selection, or DCS-Transformer. DCS-Transformer features channel selection in the computation of the attention weights and the input/output features of the MLP in the transformer block. Our DCS-Transformer is compatible with many popular and compact transformer networks, such as MobileViT and EfficientViT, and it reduces the FLOPs of the visual transformers while maintaining or even improving the prediction accuracy. In the experiments, we replace all the transformer blocks in MobileViT and EfficientViT with DCS-Transformer blocks, leading to DCS-Transformer networks with different backbones. The DCS-Transformer is motivated by reduction of Information Bottleneck, and a novel variational upper bound for the IB loss which can be optimized by SGD is derived and incorporated into the training loss of the network with DCS-Transformer. Extensive results on image classification and object detection evidence that DCS-Transformer renders compact and efficient visual transformers with comparable or much better prediction accuracy than the original visual transformers. The code of DCS-Transformer is available at https://github.com/Statistical-Deep-Learning/DCS-Transformer.