论文检索

Deep Learning · Large Language Models

Senyu Han, Hongchuan Zeng, Kai Yu, Lu Chen

Large language models (LLMs) consist of numerous Transformer modules, and while the models can perform various functions, it remains an open question of how these modules are combined to elicit distinct inherent functionalities. In this paper, we investigate the modules inside LLMs and demonstrate that, by simply masking or retaining specific attention heads during inference, LLMs can exhibit specific task functionalities without requiring explicit instructions or modifications to the model parameters. Experiments across various models and tasks reveal that LLMs inherently encode ``functional pathways'', the structured groups of interdependent attention heads that are crucial for executing specific tasks. These pathways not only govern the model's functional behaviors but also enhance parameter efficiency, as suppressing attention heads outside the pathway can improve task performance. The code is available in this repository: [https://github.com/OpenDFM/HeadsUp](https://github.com/OpenDFM/HeadsUp).

General Machine Learning · Sequential, Network, and Time Series Modeling

Andrea Cini, Alexander Jenkins, Danilo Mandic, Cesare Alippi, Filippo Maria Bianchi

We address the problem of uncertainty quantification in time series forecasting by exploiting observations at correlated sequences. Relational deep learning methods leveraging graph representations are among the most effective tools for obtaining point estimates from spatiotemporal data and correlated time series. However, the problem of exploiting relational structures to estimate the uncertainty of such predictions has been largely overlooked in the same context. To this end, we propose a novel distribution-free approach based on the conformal prediction framework and quantile regression. Despite the recent applications of conformal prediction to sequential data, existing methods operate independently on each target time series and do not account for relationships among them when constructing the prediction interval. We fill this void by introducing a novel conformal prediction method based on graph deep learning operators. Our approach, named Conformal Relational Prediction (CoRel), does not require the relational structure (graph) to be known a priori and can be applied on top of any pre-trained predictor. Additionally, CoRel includes an adaptive component to handle non-exchangeable data and changes in the input time series. Our approach provides accurate coverage and achieves state-of-the-art uncertainty quantification in relevant benchmarks.

Deep Learning · Graph Neural Networks

Yongqiang Chen, QUANMING YAO, Juzheng Zhang, James Cheng, Yatao Bian

Recently, there has been a surge of interest in extending the success of large language models (LLMs) from texts to molecules. Most existing approaches adopt a graph neural network to represent a molecule as a series of node tokens for molecule-language alignment, which, however, have overlooked the inherent hierarchical structures in molecules. Notably, higher-order molecular structures contain rich semantics of functional groups, which encode crucial biochemical functionalities of the molecules. We show that neglecting the hierarchical information in tokenization will lead to subpar molecule-language alignment and severe hallucination. To address this limitation, we propose HIerarchical GrapH Tokenization (HIGHT). HIGHT employs a hierarchical graph tokenizer that encodes the hierarchy of atom, motif, and molecular levels of informative tokens to improve the molecular perception of LLMs. HIGHT also adopts an augmented instruction tuning dataset, enriched with the hierarchical graph information, to further enhance the molecule-language alignment. Extensive experiments on 14 real-world benchmarks verify the effectiveness of HIGHT in reducing hallucination by 40%, and significant improvements in various molecule-language downstream tasks. The project is available at https: //higraphllm.github.io/.

Deep Learning · Algorithms

Anvith Thudi, Evianne Rovers, Yangjun Ruan, Tristan Thrush, Chris Maddison

Modern machine learning pipelines are increasingly combining and mixing data from diverse and disparate sources, e.g., pre-training large language models. Yet, finding the optimal data mixture is a challenging and open problem. We formalize this data mixing problem as a bi-level objective: the best mixture is the one that would lead to the best model for a downstream objective. Unfortunately, this objective is generally intractable. In this paper, we make the observation that the bi-level data mixing objective becomes convex as our model class becomes larger. We develop and study a gradient-based approach for optimizing this convex objective, which we call MixMin, and test it on language modeling and chemistry tasks. MixMin was the only method that uniformly improved the data mixture in all our experiments. With MixMin, we improved the data mixture using less than 0.2% additional compute for a pythia-$410M$ model trained on $8.2B$ tokens, resulting between 1-5% relative improvement to negative log likelihood on PIQA, ARC Easy, SciQ, and OpenWebMath. Crucially, we found that MixMin mixtures for smaller models improved training of larger models, suggesting that MixMin mixtures may be scale-invariant. When mixing bioassay data to train an XGBoost model, we saw improvements to average precision scores of $0.03-0.15$.

Theory · Optimization

Quentin Fruytier, Aryan Mokhtari, Sujay Sanghavi

Classical Mixtures of Experts (MoE) are Machine Learning models that involve partitioning the input space, with a separate "expert" model trained on each partition. Recently, MoE-based model architectures have become popular as a means to reduce training and inference costs. There, the partitioning function and the experts are both learnt jointly via gradient descent-type methods on the log-likelihood. In this paper we study theoretical guarantees of the Expectation Maximization (EM) algorithm for the training of MoE models. We first rigorously analyze EM for MoE where the conditional distribution of the target and latent variable conditioned on the feature variable belongs to an exponential family of distributions and show its equivalence to projected Mirror Descent with unit step size and a Kullback-Leibler Divergence regularizer. This perspective allows us to derive new convergence results and identify conditions for local linear convergence; In the special case of mixture of 2 linear or logistic experts, we additionally provide guarantees for linear convergence based on the signal-to-noise ratio. Experiments on synthetic and (small-scale) real-world data supports that EM outperforms the gradient descent algorithm both in terms of convergence rate and the achieved accuracy.

Applications · Computer Vision

Mohamed Ali Souibgui, Changkyu Choi, Andrey Barsky, Kangsoo Jung, Ernest Valveny, Dimosthenis Karatzas

We propose **DocVXQA**, a novel framework for visually self-explainable document question answering, where the goal is not only to produce accurate answers to questions but also to learn visual heatmaps that highlight critical regions, offering interpretable justifications for the model decision. To integrate explanations into the learning process, we quantitatively formulate explainability principles as explicit learning criteria.Unlike conventional relevance map methods that solely emphasize regions relevant to the answer, our context-aware DocVXQA delivers explanations that are contextually sufficient yet representation-efficient. This fosters user trust while achieving a balance between predictive performance and interpretability in document visual question answering applications. Extensive experiments, including human evaluation, provide strong evidence supporting the effectiveness of our method.

General Machine Learning · Everything Else

Chen Zhang, Weixin Bu, Zeyi Ren, Zhengwu Liu, Yik-Chung WU, Ngai Wong

Inferring properties of graph-structured data, *e.g.*, the solubility of molecules, essentially involves learning the implicit mapping from graphs to their properties. This learning process is often costly for graph property learners like Graph Convolutional Networks (GCNs). To address this, we propose a paradigm called Graph Nonparametric Teaching (GraNT) that reinterprets the learning process through a novel nonparametric teaching perspective. Specifically, the latter offers a theoretical framework for teaching implicitly defined (*i.e.*, nonparametric) mappings via example selection. Such an implicit mapping is realized by a dense set of graph-property pairs, with the GraNT teacher selecting a subset of them to promote faster convergence in GCN training. By analytically examining the impact of graph structure on parameter-based gradient descent during training, and recasting the evolution of GCNs—shaped by parameter updates—through functional gradient descent in nonparametric teaching, we show *for the first time* that teaching graph property learners (*i.e.*, GCNs) is consistent with teaching structure-aware nonparametric learners. These new findings readily commit GraNT to enhancing learning efficiency of the graph property learner, showing significant reductions in training time for graph-level regression (-36.62\%), graph-level classification (-38.19\%), node-level regression (-30.97\%) and node-level classification (-47.30\%), all while maintaining its generalization performance.

Optimization

Sheheryar Mehmood, Peter Ochs

Numerous optimization algorithms have a time-varying update rule thanks to, for instance, a changing step size, momentum parameter or, Hessian approximation. Often, such algorithms are used as solvers for the lower-level problem in bilevel optimization, and are unrolled when computing the gradient of the upper-level objective. In this paper, we apply unrolled or automatic differentiation to a time-varying iterative process and provide convergence (rate) guarantees for the resulting derivative iterates. We then adapt these convergence results and apply them to proximal gradient descent with variable step size and FISTA when solving partly-smooth problems. We test the convergence (rates) of these algorithms numerically through several experiments. Our theoretical and numerical results show that the convergence rate of the algorithm is reflected in its derivative iterates.

Deep Learning · Large Language Models

Shibo Jie, Yehui Tang, Kai Han, Yitong Li, Duyu Tang, Zhi-Hong Deng, Yunhe Wang

Mixture-of-Experts (MoE) activates only a subset of experts during inference, allowing the model to maintain low inference FLOPs and latency even as the parameter count scales up. However, since MoE dynamically selects the experts, all the experts need to be loaded into VRAM. Their large parameter size still limits deployment, and offloading, which load experts into VRAM only when needed, significantly increase inference latency. To address this, we propose Mixture of Lookup Experts (MoLE), a new MoE architecture that is efficient in both communication and VRAM usage. In MoLE, the experts are Feed-Forward Networks (FFNs) during training, taking the output of the embedding layer as input. Before inference, these experts can be re-parameterized as lookup tables (LUTs) that retrieves expert outputs based on input ids, and offloaded to storage devices. Therefore, we do not need to perform expert computations during inference. Instead, we directly retrieve the expert's computation results based on input ids and load them into VRAM, and thus the resulting communication overhead is negligible. Experiments show that, with the same FLOPs and VRAM usage, MoLE achieves inference speeds comparable to dense models and significantly faster than MoE with experts offloading, while maintaining performance on par with MoE. Code: https://github.com/JieShibo/MoLE.

General Machine Learning · Supervised Learning

Ben Dai

Empirical risk minimization (ERM) with a computationally feasible surrogate loss is a widely accepted approach for classification. Notably, the convexity and calibration (CC) properties of a loss function ensure consistency of ERM in maximizing accuracy, thereby offering a wide range of options for surrogate losses. In this article, we propose a novel ensemble method, namely *EnsLoss*, which extends the ensemble learning concept to combine loss functions within the ERM framework. A key feature of our method is the consideration on preserving the "legitimacy" of the combined losses, i.e., ensuring the CC properties. Specifically, we first transform the CC conditions of losses into loss-derivatives, thereby bypassing the need for explicit loss functions and directly generating calibrated loss-derivatives. Therefore, inspired by Dropout, *EnsLoss* enables loss ensembles through one training process with doubly stochastic gradient descent (i.e., random batch samples and random calibrated loss-derivatives). We theoretically establish the statistical consistency of our approach and provide insights into its benefits. The numerical effectiveness of *EnsLoss* compared to fixed loss methods is demonstrated through experiments on a broad range of 45 pairs of CIFAR10 datasets, the PCam image dataset, and 14 OpenML tabular datasets and with various deep learning architectures. Python repository and source code are available on our Github (https://github.com/statmlben/ensLoss).

Deep Learning · Algorithms

Guoqiang Zhang, John Lewis, W. Bastiaan Kleijn

In this work we present the BDIA-transformer, which is an exact bit-level reversible transformer that uses an unchanged standard architecture for inference. The basic idea is to first treat each transformer block as the Euler integration approximation for solving an ordinary differential equation (ODE) and then incorporate the technique of bidirectional integration approximation (BDIA) (originally designed for diffusion inversion) into the neural architecture, together with activation quantization to make it exactly bit-level reversible. In the training process, we let a hyper-parameter $\gamma$ in BDIA-transformer randomly take one of the two values $\{0.5, -0.5\}$ per training sample per transformer block for averaging every two consecutive integration approximations. As a result, BDIA-transformer can be viewed as training an ensemble of ODE solvers parameterized by a set of binary random variables, which regularizes the model and results in improved validation accuracy. Lightweight side information is required to be stored in the forward process to account for binary quantization loss to enable exact bit-level reversibility. In the inference procedure, the expectation $\mathbb{E}(\gamma)=0$ is taken to make the resulting architecture identical to transformer up to activation quantization. Our experiments in natural language generation, image classification, and language translation show that BDIA-transformers outperform their conventional counterparts significantly in terms of validation performance while also requiring considerably less training memory. Thanks to the regularizing effect of the ensemble, the BDIA-transformer is particularly suitable for fine-tuning with limited data. Source-code can be found via \href{https://github.com/guoqiang-zhang-x/BDIA-Transformer}{this link}.

Deep Learning · Robustness

Feiyang Wang, Xingquan Zuo, Hai Huang, Gang Chen

A key challenge in black-box adversarial attacks is the high query complexity in hard-label settings, where only the top-1 predicted label from the target deep model is accessible. In this paper, we propose a novel normal-vector-based method called Two-third Bridge Attack (TtBA). A innovative bridge direction is introduced which is a weighted combination of the current unit perturbation direction and its unit normal vector, controlled by a weight parameter $k$. We further use binary search to identify $k=k_\text{bridge}$, which has identical decision boundary as the current direction. Notably, we observe that $k=2/3 k_\text{bridge}$ yields a near-optimal perturbation direction, ensuring the stealthiness of the attack. In addition, we investigate the critical importance of local optima during the perturbation direction optimization process and propose a simple and effective approach to detect and escape such local optima. Experimental results on MNIST, FASHION-MNIST, CIFAR10, CIFAR100, and ImageNet datasets demonstrate the strong performance and scalability of our approach. Compared to state-of-the-art non-targeted and targeted attack methods, TtBA consistently delivers superior performance across most experimented datasets and deep learning models. Code is available at https://anonymous.4open.science/r/TtBA-6ECF.

Deep Learning · Robustness

Thomas Massena, Léo Andéol, Thibaut Boissin, Franck Mamalet, Corentin FRIEDRICH, Mathieu Serrurier, Sébastien Gerchinovitz

Conformal Prediction (CP) has proven to be an effective post-hoc method for improving the trustworthiness of neural networks by providing prediction sets with finite-sample guarantees. However, under adversarial attacks, classical conformal guarantees do not hold anymore: this problem is addressed in the field of Robust Conformal Prediction. Several methods have been proposed to provide robust CP sets with guarantees under adversarial perturbations, but, for large scale problems, these sets are either too large or the methods are too computationally demanding to be deployed in real life scenarios. In this work, we propose a new method that leverages Lipschitz-bounded networks to precisely and efficiently estimate robust CP sets. When combined with a 1-Lipschitz robust network, we demonstrate that our *lip-rcp* method outperforms state-of-the-art results in both the size of the robust CP sets and computational efficiency in medium and large-scale scenarios such as ImageNet. Taking a different angle, we also study vanilla CP under attack, and derive new worst-case coverage bounds of vanilla CP sets, which are valid simultaneously for all adversarial attack levels. Our *lip-rcp* method makes this second approach as efficient as vanilla CP while also allowing robustness guarantees.

Applications · Computer Vision

XINMIN QIU, Gege Chen, Bonan Li, Congying Han, Tiande Guo, Zicheng Zhang

Blind face restoration (BFR), which involves converting low-quality (LQ) images into high-quality (HQ) images, remains challenging due to complex and unknown degradations. While previous diffusion-based methods utilize feature extractors from LQ images as guidance, using raw LQ images directly as the starting point for the reverse diffusion process offers a theoretically optimal solution. In this work, we propose Pseudo-Hashing Image-to-image Schrödinger Bridge (P-I2SB), a novel framework inspired by optimal mass transport problems, which enhances the restoration potential of Schrödinger Bridge (SB) by correcting data distributions and effectively learning the optimal transport path between any two data distributions. Notably, we theoretically explore and identify that existing methods are limited by the optimality and reversibility of solutions in SB, leading to suboptimal performance. Our approach involves preprocessing HQ images during training by hashing them into pseudo-samples according to a rule related to LQ images, ensuring structural similarity in distribution. This guarantees optimal and reversible solutions in SB, enabling the inference process to learn effectively and allowing P-I2SB to achieve state-of-the-art results in BFR, with more natural textures and retained inference speed compared to previous methods.

Social Aspects · Safety

Daiheng Gao, Shilin Lu, Wenbo Zhou, Jiaming Chu, Jie Zhang, Mengxi Jia, Bang Zhang, Zhaoxin Fan, Weiming Zhang

Removing unwanted concepts from large-scale text-to-image (T2I) diffusion models while maintaining their overall generative quality remains an open challenge. This difficulty is especially pronounced in emerging paradigms, such as Stable Diffusion (SD) v3 and Flux, which incorporate flow matching and transformer-based architectures. These advancements limit the transferability of existing concept-erasure techniques that were originally designed for the previous T2I paradigm (e.g., SD v1.4). In this work, we introduce EraseAnything, the first method specifically developed to address concept erasure within the latest flow-based T2I framework. We formulate concept erasure as a bi-level optimization problem, employing LoRA-based parameter tuning and an attention map regularizer to selectively suppress undesirable activations. Furthermore, we propose a self-contrastive learning strategy to ensure that removing unwanted concepts does not inadvertently harm performance on unrelated ones. Experimental results demonstrate that EraseAnything successfully fills the research gap left by earlier methods in this new T2I paradigm, achieving state-of-the-art performance across a wide range of concept erasure tasks.

Social Aspects · Privacy

Matthew Wicker, Philip Sosnin, Igor Shilov, Adrianna Janik, Mark Müller, Yves-Alexandre de Montjoye, Adrian Weller, Calvin Tsay

We study private prediction where differential privacy is achieved by adding noise to the outputs of a non-private model. Existing methods rely on noise proportional to the global sensitivity of the model, often resulting in sub-optimal privacy-utility trade-offs compared to private training. We introduce a novel approach for computing dataset-specific upper bounds on prediction sensitivity by leveraging convex relaxation and bound propagation techniques. By combining these bounds with the smooth sensitivity mechanism, we significantly improve the privacy analysis of private prediction compared to global sensitivity-based approaches. Experimental results across real-world datasets in medical image classification and natural language processing demonstrate that our sensitivity bounds are can be orders of magnitude tighter than global sensitivity. Our approach provides a strong basis for the development of novel privacy preserving technologies.

Applications · Robotics

Amber Xie, Oleh Rybkin, Dorsa Sadigh, Chelsea Finn

Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert demonstrations.To address these shortcomings, we propose Latent Diffusion Planning (LDP), a modular approach consisting of a planner which can leverage action-free demonstrations, and an inverse dynamics model which can leverage suboptimal data, that both operate over a learned latent space. First, we learn a compact latent space through a variational autoencoder, enabling effective forecasting of future states in image-based domains. Then, we train a planner and an inverse dynamics model with diffusion objectives. By separating planning from action prediction, LDP can benefit from the denser supervision signals of suboptimal and action-free data.On simulated visual robotic manipulation tasks, LDP outperforms state-of-the-art imitation learning approaches, as they cannot leverage such additional data.

Theory · Everything Else

Sunil Madhow, Dheeraj Baby, Yu-Xiang Wang

In order to attain optimal rates, state-of-the-art algorithms for non-parametric regression require that a hyperparameter be tuned according to the smoothness of the ground truth (Tibshirani, 2014). This amounts to an assumption of oracle access to certain features of the data-generating process. We present a parameter-free algorithm for offline non-parametric regression over $TV_1$-bounded functions. By feeding offline data into an optimal online denoising algorithm styled after (Baby et al., 2021), we are able to use change-points to adaptively select knots that respect the geometry of the underlying ground truth. We call this procedure AKORN (Adaptive Knots gener- ated Online for RegressioN splines). By combining forward and backward passes over the data, we obtain an estimator whose empirical performance is close to Trend Filtering (Kim et al., 2009; Tibshirani, 2014), even when we provide the latter with oracle knowledge of the ground truth’s smoothness.

Social Aspects · Alignment

Ariel Procaccia, Benjamin Schiffer, Shirley Zhang

A key challenge in training Large Language Models (LLMs) is properly aligning them with human preferences. Reinforcement Learning with Human Feedback (RLHF) uses pairwise comparisons from human annotators to train reward functions and has emerged as a popular alignment method. However, input datasets in RLHF can be unbalanced due to adversarial manipulation or inadvertent repetition. Therefore, we want RLHF algorithms to perform well even when the set of alternatives is not uniformly distributed. Drawing on insights from social choice theory, we introduce robustness to approximate clones, a desirable property of RLHF algorithms which requires that adding near-duplicate alternatives does not significantly change the learned reward function. We first demonstrate that the standard RLHF algorithm based on regularized maximum likelihood estimation (MLE) fails to satisfy this property. We then propose the weighted MLE, a new RLHF algorithm that modifies the standard regularized MLE by weighting alternatives based on their similarity to other alternatives. This new algorithm guarantees robustness to approximate clones while preserving desirable theoretical properties.

Deep Learning · Attention Mechanisms

Yunfeng Liao, Jiawen Guan, Xiucheng Li

Deep models have recently achieved remarkable performances in solving partial differential equations (PDEs). The previous methods are mostly focused on PDEs arising in Euclidean spaces with less emphasis on the general manifolds with rich geometry. Several proposals attempt to account for the geometry by exploiting the spatial coordinates but overlook the underlying intrinsic geometry of manifolds. In this paper, we propose a Curvature-aware Graph Attention for PDEs on manifolds by exploring the important intrinsic geometric quantities such as curvature and discrete gradient operator. It is realized via parallel transport and tensor field on manifolds. To accelerate computation, we present three curvature-oriented graph embedding approaches and derive closed-form parallel transport equations, and a subtree partition method is also developed to promote parameter-sharing. Our proposed curvature-aware attention can be used as a replacement for vanilla attention, and experiments show that it significantly improves the performance of the existing methods for solving PDEs on manifolds. Our code is available at https://github.com/Supradax/CurvGT.