论文检索

Jun Sun, Xinxin Zhang, Simin Hong, Jian Zhu, Xiang Gao

Multimodal learning, while contributing to numerous success stories across various fields, faces the challenge of prohibitively expensive manual annotation. To address the scarcity of annotated data, a popular solution is unsupervised domain adaptation, which has been extensively studied in unimodal settings yet remains less explored in multimodal settings. In this paper, we investigate heterogeneous multimodal domain adaptation, where the primary challenge is the varying domain shifts of different modalities from the source to the target domain. We first introduce the information bottleneck method to learn representations for each modality independently, and then match the source and target domains in the representation space with correlation alignment. To balance the domain alignment of all modalities, we formulate the problem as a multi-objective task, aiming for a Pareto optimal solution. By exploiting the properties specific to our model, the problem can be simplified to a quadratic programming problem. Further approximation yields a closed-form solution, leading to an efficient modality-balanced multimodal domain adaptation algorithm. The proposed method features Balanced multi-objective optimization for multimodal domain adaptation, termed Boomda. Extensive empirical results showcase the effectiveness of the proposed approach and demonstrate that Boomda outperforms the competing schemes.

Jiangfeng Sun, SiHao He, Zhonghong Ou, Meina Song

Multimodal sentiment analysis (MSA) aims to infer emotional states by effectively integrating textual, acoustic, and visual modalities. Despite notable progress, existing multimodal fusion methods often neglect modality-specific structural dependencies and semantic misalignment, limiting their quality, interpretability, and robustness. To address these challenges, we propose a novel framework called the Structural-Semantic Unifier (SSU), which systematically integrates modality-specific structural information and cross-modal semantic grounding for enhanced multimodal representations. Specifically, SSU dynamically constructs modality-specific graphs by leveraging linguistic syntax for text and a lightweight, text-guided attention mechanism for acoustic and visual modalities, thus capturing detailed intra-modal relationships and semantic interactions. We further introduce a semantic anchor, derived from global textual semantics, that serves as a cross-modal alignment hub, effectively harmonizing heterogeneous semantic spaces across modalities. Additionally, we develop a multi-view contrastive learning objective that promotes discriminability, semantic consistency, and structural coherence across intra- and inter-modal views. Extensive evaluations on two widely-used benchmark datasets, CMU-MOSI and CMU-MOSEI, demonstrate that SSU consistently achieves state-of-the-art performance while significantly reducing computational overhead compared to prior methods. Comprehensive qualitative analyses further validate SSU’s interpretability and its ability to capture nuanced emotional patterns through semantically-grounded interactions.

Chuxiong Sun, Dunqi Yao, Rui Wang, Wenwen Qiang, Changwen Zheng, Jiangmeng Li

Exploration in sparse-reward tasks remains a fundamental challenge in multi-agent reinforcement learning (MARL) due to complex inter-agent interactions and the expansive exploration space. To address this issue, we propose Targeted Multi-Agent Exploration (TMAE), a novel framework that uncovers the causal relationships between the state space and the reward function, thereby reducing the exploration space and enabling more targeted exploration. Specifically, we construct a structural causal model (SCM) to model the causality between sub-state variables and sparse rewards, providing a robust analytical foundation for subsequent causal inference. Through counterfactual causal intervention, TMAE identifies the most critical subspaces for discovering rare but pivotal events while filtering out confounders. By incorporating these causal insights into the exploration process, TMAE prioritizes subspaces with stronger causal effects on sparse rewards, significantly enhancing exploration efficiency. We evaluate TMAE on a range of MARL benchmarks featuring sparse rewards, consistently demonstrating superior exploration efficiency compared to state-of-the-art methods. Furthermore, visualized causal insights derived from TMAE reveal its ability to effectively capture intricate dependencies and priorities in targeted exploration, showcasing strong alignment with prior domain knowledge.

Chuxiong Sun, Peng He, Qirui Ji, Zehua Zang, Jiangmeng Li, Rui Wang, Wei Wang

Communication is essential in coordinating the behaviors of multiple agents. However, existing methods primarily emphasize content, timing, and partners for information sharing, often neglecting the critical aspect of integrating shared information. This gap can significantly impact agents' ability to understand and respond to complex, uncertain interactions, thus affecting overall communication efficiency. To address this issue, we introduce M2I2, a novel framework designed to enhance the agents' capabilities to assimilate and utilize received information effectively. M2I2 equips agents with advanced capabilities for masked state modeling and joint-action prediction, enriching their perception of environmental uncertainties and facilitating the anticipation of teammates' intentions. This approach ensures that agents are furnished with both comprehensive and relevant information, bolstering more informed and synergistic behaviors. Moreover, we propose a Dimensional Rational Network, innovatively trained via a meta-learning paradigm, to identify the importance of dimensional pieces of information, evaluating their contributions to decision-making and auxiliary tasks. Then, we implement an importance-based heuristic for selective information masking and sharing. This strategy optimizes the efficiency of masked state modeling and the rationale behind information sharing. We evaluate M2I2 across diverse multi-agent tasks, the results demonstrate its superior performance, efficiency, and generalization capabilities, over existing state-of-the-art methods in various complex scenarios.

Chengwei Sun, Jiwei Wei, Shiyuan He, Zeyu Ma, Yuyang Zhou, Ran Ran, Jie Zou, Yang Yang

Fully fine-tuning large pre-trained models for each downstream task is impractical due to prohibitive memory, computation, and storage costs. Although parameter-efficient fine-tuning (PEFT) methods address this issue, leading methods like LoRA still exhibit linear scaling of trainable parameters with hidden size. Recent studies have explored PEFT in the frequency domain to reduce computational costs by employing fast Fourier transform and discrete cosine transform with sparse frequency selection. These methods rely on global frequency representations that lack spatial locality and disperse energy across the domain. As a result, sparse coefficient selection struggles to preserve fine-grained structural information and often introduces artifacts such as ringing near boundaries. To address these limitations, we propose DWTSG, a novel PEFT framework based on discrete wavelet transform (DWT) and subband guidance. DWTSG decomposes pre-trained weights into four wavelet subbands that jointly encode global context and local details. It fine-tunes only the most informative coefficients in each subband through an energy-based selection strategy that prioritizes coefficients based on their individual importance and interactions. Finally, inverse DWT reconstructs the updated weights, enabling efficient and precise adaptation. Extensive experiments on natural language understanding, commonsense reasoning, and image classification demonstrate that DWTSG outperforms existing PEFT methods, achieving superior performance and higher parameter efficiency.

Chenglu Sun, Shuo Shen, Haonan Hu, Wei Zhou, Chen Chen

Despite advancements in language-controlled reinforcement learning (LC-RL) for basic domains and straightforward commands (e.g., object manipulation and navigation), effectively extending LC-RL to comprehend and execute high-level or abstract instructions in complex, multi-agent environments, such as football games, remains a significant challenge. To address this gap, we introduce Language-Controlled Diverse Style Policies (LCDSP), a novel LC-RL paradigm specifically designed for complex scenarios. LCDSP comprises two key components: a Diverse Style Training (DST) method and a Style Interpreter (SI). The DST method efficiently trains a single policy capable of exhibiting a wide range of diverse behaviors by modulating agent actions through style parameters (SP). The SI is designed to accurately and rapidly translate high-level language instructions into these corresponding SP. Through extensive experiments in a complex 5v5 football environment, we demonstrate that LCDSP effectively comprehends abstract tactical instructions and accurately executes the desired diverse behavioral styles, showcasing its potential for complex, real-world applications.

Cong Su, Qiaoyu Tan, Carlotta Domeniconi, Lizhen Cui, Jun Wang, Guoxian Yu

Fairness-aware machine learning aims to build predictive models that comply with fairness requirements, particularly concerning sensitive attributes such as race, gender, and age. Among causality-based fairness notions, counterfactual fairness is widely adopted for its individual-level guarantees, requiring that an individual’s predicted outcome remains unchanged in a counterfactual world where its sensitive attribute is altered. However, existing methods critically assume that the true causal graph is fully known, which is rarely the case in practice. Moreover, counterfactual fairness suffers from inherent identifiability limitations, as counterfactual quantities cannot always be uniquely estimated from observational data, especially under incomplete causal knowledge. To address these challenges, we propose a principled framework (CF-ICG) for counterfactual fairness under imperfectly known causal graphs, e.g., Completed Partially Directed Acyclic Graphs (CPDAGs). We first introduce a criterion to determine the identifiability, and bound the counterfactual quantities under CPDAGs. Building upon this, we develop an efficient local algorithm that avoids the exhaustive enumeration of all DAGs, ensuring robustness against worst-case fairness violations. Experimental results on synthetic and real-world datasets demonstrate the practical effectiveness and theoretical soundness of CF-ICG.

Chao Su, Yanan Li, Xu Wang, Yingke Chen, Huiming Zheng, Dezhong Peng, Yuan Sun

Cross-modal hashing (CMH) has achieved remarkable success in large-scale cross-modal retrieval due to its low storage cost and high computational efficiency. However, most existing CMH methods rely on accurately annotated training data, which is often impractical in real-world applications due to the high cost and limited scalability of data annotation. In practice, annotators typically assign a candidate label set rather than a single precise label to each sample pair, resulting in partial labels with inherent ambiguity. Such ambiguous supervision poses significant challenges to conventional CMH methods that assume reliable and unambiguous labels. In this paper, we investigate a less-touched yet meaningful problem, i.e., cross-modal hashing with partial labels (PLCMH). PLCMH faces two major challenges: label ambiguity and modality-alignment barriers induced by misleading supervision. To address these issues, we propose a new approach named Ambiguity-Tolerant Cross-Modal Hashing (ATCH). Specifically, ATCH presents a Local Consensus Disambiguation (LCD) mechanism that resolves label ambiguity by effectively inferring stable and accurate label confidence based on local consensus within the Hamming space. Moreover, ATCH proposes a Confidence-Aware Contrastive Hashing (CACH) mechanism that derives both pseudo labels and trustworthiness scores from the label confidence vectors to learn discriminative hash codes, leading to effective modality alignment. Extensive experiments on three multimodal datasets demonstrate the superiority of ATCH.

Paul Strang, Zacharie Alès, Côme Bissuel, Olivier Juan, Safia Kedad-Sidhoum, Emmanuel Rachelson

Mixed-Integer Linear Programming (MILP) lies at the core of many real-world combinatorial optimization (CO) problems, traditionally solved by branch-and-bound (B&B). A key driver influencing B&B solvers efficiency is the variable selection heuristic that guides branching decisions. Looking to move beyond static, hand-crafted heuristics, recent work has explored adapting traditional reinforcement learning (RL) algorithms to the B&B setting, aiming to learn branching strategies tailored to specific MILP distributions. In parallel, RL agents have achieved remarkable success in board games, a very specific type of combinatorial problems, by leveraging environment simulators to plan via Monte Carlo Tree Search (MCTS). Building on these developments, we introduce Plan-and-Branch-and-Bound (PlanB&B), a model-based reinforcement learning (MBRL) agent that leverages a learned internal model of the B&B dynamics to discover improved branching strategies. Computational experiments empirically validate our approach, with our MBRL branching agent outperforming previous state-of-the-art RL methods across four standard MILP benchmarks.

Roland Stolz, Michael Eichelbeck, Matthias Althoff

In reinforcement learning (RL), it is often advantageous to consider additional constraints on the action space to ensure safety or action relevance. Existing work on such action-constrained RL faces challenges regarding effective policy updates, computational efficiency, and predictable runtime. Recent work proposes to use truncated normal distributions for stochastic policy gradient methods. However, the computation of key characteristics, such as the entropy, log-probability, and their gradients, becomes intractable under complex constraints. Hence, prior work approximates these using the non-truncated distributions, which severely degrades performance. We argue that accurate estimation of these characteristics is crucial in the action-constrained RL setting, and propose efficient numerical approximations for them. We also provide an efficient sampling strategy for truncated policy distributions and validate our approach on three benchmark environments, which demonstrate significant performance improvements when using accurate estimations.

Gabriela Ben Melech Stan, Estelle Aflalo, Avinash Madasu, Vasudev Lal, Phillip Howard

Training models on synthetic data has emerged as an increasingly important strategy for improving the performance of generative AI. This approach is particularly helpful for large multimodal models (LMMs) due to the relative scarcity of high-quality paired image-text data compared to language-only data. While a variety of methods have been proposed for generating large multimodal datasets, they do not tailor the synthetic data to address specific deficiencies in the reasoning abilities of LMMs which will be trained with the generated dataset. In contrast, humans often learn in a more efficient manner by seeking out examples related to the types of reasoning where they have failed previously. Inspired by this observation, we propose a new approach for synthetic data generation which is grounded in the analysis of an existing LMM's reasoning failures. Our methodology leverages frontier models to automatically analyze errors produced by a weaker LMM and propose new examples which can be used to correct the reasoning failure via additional training, which are then further filtered to ensure high quality. We generate a large multimodal instruction tuning dataset containing over 553k examples using our approach and conduct extensive experiments demonstrating its utility for improving the performance of LMMs on multiple downstream tasks. Our results show that models trained on our synthetic data can even exceed the performance of LMMs trained on an equivalent amount of additional real data, demonstrating the high value of generating synthetic data targeted to specific reasoning failure modes in LMMs.

Julian Spravil, Sebastian Houben, Sven Behnke

Cross-lingual, cross-task transfer is challenged by task-specific data scarcity, which becomes more severe as language support grows and is further amplified in vision-language models (VLMs). We investigate multilingual generalization in encoder-decoder transformer VLMs to enable zero-shot image captioning in languages encountered only in the translation task. In this setting, the encoder must learn to generate generalizable, task-aware latent vision representations to instruct the decoder via inserted cross-attention layers. To analyze scaling behavior, we train Florence-2 based and Gemma-2 based models (0.4B to 11.2B parameters) on a synthetic dataset using varying compute budgets. While all languages in the dataset have image-aligned translations, only a subset of them include image captions. Notably, we show that captioning can emerge using a language prefix, even when this language only appears in the translation task. We find that indirect learning of unseen task-language pairs adheres to scaling laws that are governed by the multilinguality of the model, model size, and seen training samples. Finally, we demonstrate that the scaling laws extend to downstream tasks, achieving competitive performance through fine-tuning in multimodal machine translation (Multi30K, CoMMuTE), lexical disambiguation (CoMMuTE), and image captioning (Multi30K, XM3600, COCO Karpathy).

Jules Soria, Zakaria Chihani, Julien Girard-Satabin, Alban Grastien, Romain Xu-Darme, Daniela Cancila

Case-based reasoning networks are machine-learning models that make predictions based on similarity between the input and prototypical parts of training samples, called prototypes. Such models are able to explain each decision by pointing to the prototypes that contributed the most to the final outcome. As the explanation is a core part of the prediction, they are often qualified as "interpretable by design". While promising, we show that such explanations are sometimes misleading, which hampers their usefulness in safety-critical contexts. In particular, several instances may lead to different predictions and yet have the same explanation. Drawing inspiration from the field of formal eXplainable AI (formal XAI), we propose Abductive Latent Explanations (ALEs), a formalism to express sufficient conditions on the intermediate (latent) representation of the instance that imply the prediction. Our approach combines the inherent interpretability of case-based reasoning models and the guarantees provided by formal XAI. We propose a solver-free and scalable algorithm for generating ALEs based on three distinct paradigms, compare them, and present the feasibility of our approach on diverse datasets for both standard and fine-grained image classification.

Yu Song, Zhigang Hua, Yan Xie, Bingheng Li, Jingzhe Liu, Bo Long, Jiliang Tang, Hui Liu

Graph-structured data plays a pivotal role in modeling complex relationships. However, real-world graphs are often incomplete due to data collection and observational constraints, severely limiting the effectiveness of modern graph learning pipelines. While existing Graph Data Augmentation (GDA) methods attempt to refine graph structures for improved downstream performance, they are typically label-dependent, computationally expensive, and inherently transductive, limiting their applicability in practical scenarios. In this work, we present a novel feature-centric graph data augmentation framework that bypasses explicit structure modeling by operating directly in the embedding space. Through a self-supervised inverse masking process, our method captures latent ties between observed and complete graphs, enabling recovery of unobserved structural signals through refined node representations. To enhance robustness under noisy and sparse supervision, we introduce a message regularizer and a bootstrap strategy for effective training and generalization. Evaluated on ten graph datasets spanning multiple domains, our approach, SelfAug, consistently outperforms state-of-the-art methods in both accuracy and efficiency across inductive and cold-start settings, highlighting its potential as a scalable and generalizable solution for real-world graph learning scenarios.

Xinxin Song, Yuxiao Cheng, Tingxiong Xiao, Jinli Suo

Time series analysis is crucial in various fields such as healthcare and finance. However, environmental variations and the inherent non-stationarity of time series data often lead to out-of-distribution (OOD) scenarios, consequently causing model performance degradation. Most existing OOD generalization methods primarily focus on images or text, leaving time series analysis relatively underexplored. In this paper, we propose COGS, a novel framework that incorporates causal representation learning into the OOD generalization of time series. By imposing structural priors, our method identifies latent variables and learns a causal graph to disentangle causal variables from non-causal ones. These causal variables are then used to learn domain-invariant representations for stable prediction. Moreover, to tackle the challenge of the absence of domain labels, we further introduce a prototype-based domain discovery algorithm that infers domain labels in an unsupervised manner. The entire framework is optimized in a two-phase iterative manner, resulting in robust OOD performance. Extensive experiments on multiple real-world time series datasets demonstrate that our method achieves competitive performance compared to baseline methods.

Tianle Song, Chenhao Lin, Yang Cao, Zhengyu Zhao, Jiahao Sun, Chong Zhang, Le Yang, Chao Shen

Mobile motion sensors such as accelerometers and gyroscopes are now ubiquitously accessible by third-party apps via standard APIs. While enabling rich functionalities like activity recognition and step counting, this openness has also enabled unregulated inference of sensitive user traits, such as gender, age, and even identity, without user consent. Existing privacy-preserving techniques, such as GAN-based obfuscation or differential privacy, typically require access to the full input sequence, introducing latency that is incompatible with real-time scenarios. Worse, they tend to distort temporal and semantic patterns, degrading the utility of the data for benign tasks like activity recognition. To address these limitations, we propose the Predictive Adversarial Transformation Network (PATN), a real-time privacy-preserving framework that leverages historical signals to generate adversarial perturbations proactively. The perturbations are applied immediately upon data acquisition, enabling continuous protection without disrupting application functionality. Experiments on two datasets demonstrate that PATN substantially degrades the performance of privacy inference models, achieving Attack Success Rate (ASR) of 40.11% and 44.65% (reducing inference accuracy to near-random) and increasing the Equal Error Rate (EER) from 8.30% and 7.56% to 41.65% and 46.22%. On ASR, PATN outperforms baseline methods by 16.16% and 31.96%, respectively.

Shezheng Song, Kangcheng Ding, Shan Zhao, Shasha Li, Xiaopeng Li, Chengyu Wang, Qian Wan, Bin Ji, Jie Yu

Multimodal Large Language Models (MLLMs) integrate text and images for complex reasoning tasks, but efficiently utilizing image remains a challenge due to redundancy and noise. Traditional methods take the entire image features as visual prompt into the MLLMs, leading to excessive visual tokens that disrupt textual information expression. Thus, recent studies treat image features as visual knowledge, storing them in the feed-forward network for retrieval when needed. These methods, completely removing images from the input, may hinder the activation of image-related knowledge. Besides, current visual knowledge focuses on fine-grained details but overlooks the hierarchical process of visual perception. As described in feature integration theory, global structure is first processed before details are integrated. Ignoring this process may lead to a fragmented visual understanding, making it difficult to capture high-level semantic relationships. To overcome these issues, we propose a novel image utilization mechanism in MLLMs. We leverage a compression-based attention mechanism to generate the compressed visual prompt, which not only mitigates the interference of excessively long visual prompts but also preserves crucial visual information necessary for activating knowledge in the MLLM. Furthermore, we extract hierarchical visual features as visual knowledge using wavelet transforms, allowing the model to capture both global structures and fine-grained details. Experiments show that our method achieves state-of-the-art performance.

Qipeng Song, Nan Yang, Ziqi Xu, Yue Li, Wei Shao, Feng Xia

Machine unlearning aims to eliminate the influence of specific data from trained models to ensure privacy compliance. However, most existing methods assume full access to the original training dataset, which is often impractical. We address a more realistic yet challenging setting: few-shot zero-glance, where only a small subset of the retained data is available and the forget set is entirely inaccessible. We introduce GFOES, a novel framework comprising a Generative Feedback Network (GFN) and a two-phase fine-tuning procedure. GFN synthesises Optimal Erasure Samples (OES), which induce high loss on target classes, enabling the model to forget class-specific knowledge without access to the original forget data, while preserving performance on retained classes. The two-phase fine-tuning procedure enables aggressive forgetting in the first phase, followed by utility restoration in the second. Experiments on three image classification datasets demonstrate that GFOES achieves effective forgetting at both logit and representation levels, while maintaining strong performance using only 5% of the original data. Our framework offers a practical and scalable solution for privacy-preserving machine learning under data-constrained conditions.

Lingyun Song, Ziyao Chen, Kang Pan, Xiaolin Han, Xinbiao Gan, Yudai Pan, Xiaofan Sun, Xiaoqi Wang, Xuequn Shang

Multimodal Large Language Models (MLLMs) employing the Mixture-of-Experts (MoE) structure exhibit encouraging results in visual language tasks. However, they struggle with catastrophic forgetting due to a lack of effective collaboration among experts and negative transfer across tasks. This happens because the router typically employed in MoE for managing expert assignments is inadequate when there are significant shifts in data distribution across various tasks. A drop in the effectiveness of earlier tasks is caused by negative transfer, which occurs due to conflicts in shared knowledge between tasks, disturbing the knowledge already acquired. To address these issues, we propose the Knowledge Space Synergy Framework in Mixture of Experts (KSS-MoE) for Continual Visual Instruction Tuning (CVIT). It dynamically combines the knowledge subspaces of experts to improve the integration of fine-grained complementary knowledge and collaborative abilities of experts, thus addressing the limitations of the basic router. Furthermore, we introduce a general expert that maintains orthogonal subspaces for shared knowledge, enabling effective cross-task knowledge utilization while reducing negative transfer. Extensive experiments conducted on eight CVIT tasks confirm the excellence of KSS-MoE, showcasing its top-tier performance.

Chuancheng Song, Hanyang Shen, Yan Dong, Xixun Lin, Yanmin Shang, Yanan Cao

Graph OOD detection is crucial in open-world scenarios, where OOD samples may manifest in diverse forms such as open-set deviations, feature-similar shifts, and structural anomalies, each exhibiting distinct geometric characteristics. However, most existing methods adopt a one-size-fits-all geometric assumption (typically Euclidean space), which inadequately captures the diverse nature of real-world distribution shifts. Therefore, adaptively selecting geometric spaces according to the properties of OOD samples is critical for their effective representation and reliable identification. Motivated by this, we revisit the graph OOD detection task under diverse distribution shifts and propose UniGOD, a unified framework serving as a graph foundation model for this task. UniGOD comprises two core modules: GeoUP and DynEVO. GeoUP module adaptively perceives the geometric space (such as Euclidean, hyperbolic, and hyperspherical space) by learning the curvature k of Riemannian manifolds. DynEVO module leverages the dynamic nature of neural SDEs to reveal pronounced uncertainty differences between ID/OOD samples, which are reflected in the divergent evolutionary trajectories of node embeddings induced by k-GNN iterations. With the geometry-dynamics coupling mechanism of the above two modules, UniGOD effectively captures the diverse distribution shifts. Extensive experiments demonstrate its superior performance over existing SOTA methods.