论文检索

Weigang Lu, Ziyu Guan, Wei Zhao, Yaming Yang, Yujie Sun, Zheng Liang, Yibing Zhan, Dapeng Tao

GNN-to-MLP (G2M) methods have emerged as a promising approach to accelerate Graph Neural Networks (GNNs) by distilling their knowledge into simpler Multi-Layer Perceptrons (MLPs). These methods bridge the gap between the expressive power of GNNs and the computational efficiency of MLPs, making them well-suited for resource-constrained environments. However, existing G2M methods are limited by their inability to flexibly adjust inference cost and accuracy dynamically, a critical requirement for real-world applications where computational resources and time constraints can vary significantly. To address this, we introduce a Progressive framework designed to offer flexible and on-demand trade-offs between inference cost and accuracy for GNN-to-MLP knowledge distillation (ProGMLP). ProGMLP employs a Progressive Training Structure (PTS), where multiple MLP students are trained in sequence, each building on the previous one. Furthermore, ProGMLP incorporates Progressive Knowledge Distillation (PKD) to iteratively refine the distillation process from GNNs to MLPs, and Progressive Mixup Augmentation (PMA) to enhance generalization by progressively generating harder mixed samples. Our approach is validated through comprehensive experiments on eight real-world graph datasets, demonstrating that ProGMLP maintains high accuracy while dynamically adapting to varying runtime scenarios, making it highly effective for deployment in diverse application settings.

Pengqian Lu, Jie Lu, Anjin Liu, En Yu, Guangquan Zhang

Existing drift detection methods focus on designing sensitive test statistics. They treat the detection threshold as a fixed hyperparameter, set once to balance false alarms and late detections, and applied uniformly across all datasets and over time. However, maintaining model performance is the key objective from the perspective of machine learning, and we observe that model performance is highly sensitive to this threshold. This observation inspires us to investigate whether a dynamic threshold could be provably better. In this paper, we prove that a threshold that adapts over time can outperform any single fixed threshold. The main idea of the proof is that a dynamic strategy, constructed by combining the best threshold from each individual data segment, is guaranteed to outperform any single threshold that apply to all segments. Based on the theorem, we propose a Dynamic Threshold Determination algorithm. It enhances existing drift detection frameworks with a novel comparison phase to inform how the threshold should be adjusted. Extensive experiments on a wide range of synthetic and real-world datasets, including both image and tabular data, validate that our approach substantially enhances the performance of state-of-the-art drift detectors.

Junkai Lu, Peng Chen, Chenjuan Guo, Yang Shu, Meng Wang, Bin Yang

Time series forecasting is critical for decision making across dynamic domains such as energy, finance, transportation, and cloud computing. However, real-world time series often exhibit non-stationarity, including temporal distribution shifts and spectral variability, which poses significant challenges for existing long-term time series forecasting methods. In this paper, we propose DTAF, a dual-branch framework that addresses non-stationarity in both the temporal and frequency domains. For the temporal domain, the Temporal Stabilizing Fusion (TFS) module employs a non-stationary mix of experts (MOE) filter to disentangle and suppress temporal non-stationary patterns while preserving long-term dependencies. For the frequency domain, the Frequency Wave Modeling (FWM) module applies frequency differencing to dynamically highlight components with significant spectral shifts. By fusing the complementary outputs of TFS and FWM, DTAF generates robust forecasts that adapt to both temporal and frequency domain non-stationarity. Extensive experiments on multiple real-world benchmarks demonstrate that DTAF outperforms state-of-the-art baselines, yielding significant improvements in forecasting accuracy under non-stationary conditions.

Aojun Lu, Tao Feng, Hangjie Yuan, Chunhui Ding, Yanan Sun

Continual Learning (CL) seeks to enable neural networks to incrementally acquire new knowledge (plasticity) while retaining existing knowledge (stability). Although pre-trained models (PTMs) have provided a strong foundation for CL, existing approaches face a fundamental challenge in balancing these two competing objectives. Current methods typically address stability by freezing the PTM backbone, which severely limits the model's plasticity, particularly when incoming data distribution diverges largely from the pre-training data. Alternatively, sequentially fine-tuning the entire PTM can adapt to new knowledge but often leads to catastrophic forgetting, highlighting the critical stability-plasticity trade-off in PTM-based CL. To address this limitation, we propose Adapting PTMs before the core CL process (ACL), a novel framework that introduces a plug-and-play adaptation phase prior to learning each new task. During this phase, ACL refines the PTM backbone by aligning embeddings with their original class prototypes while distancing them from irrelevant classes. This mechanism theoretically and empirically demonstrates desirable balance between stability and plasticity, significantly improving CL performance across benchmarks and integrated methods.

Afonso Lourenço, João Rodrigo, João Gama, Goreti Marreiros

The Internet of Things generates massive data streams, with edge computing emerging as a key enabler for online IoT applications and 5G networks. Edge solutions facilitate real-time machine learning inference, but also require continuous adaptation to concept drifts. While extensions of the Very Fast Decision Tree (VFDT) remain state-of-the-art for tabular stream mining, their unregulated growth limit efficiency, particularly in ensemble settings where post-pruning at the individual tree level is seldom applied. This paper presents DFDT, a novel memory-constrained algorithm for online learning. DFDT employs activity-aware pre-pruning, dynamically adjusting splitting criteria based on leaf node activity: low-activity nodes are deactivated to conserve resources, moderately active nodes split under stricter conditions, and highly active nodes leverage a skipping mechanism for accelerated growth. Additionally, adaptive grace periods and tie thresholds allow DFDT to modulate splitting decisions based on observed data variability, enhancing the accuracy–memory–runtime trade-off while minimizing the need for hyperparameter tuning. An ablation study reveals three DFDT variants suited to different resource profiles. Fully compatible with existing ensemble frameworks, DFDT provides a drop-in alternative to standard VFDT-based learners.

Yunbo Long, Jiaquan Zhang, Xi Chen, Alexandra Brintrup

Clustering non-independent and identically distributed (non-IID) data under local differential privacy (LDP) in federated settings presents a critical challenge: preserving privacy while maintaining accuracy without iterative communication. Existing one-shot methods rely on unstable pairwise centroid distances or neighborhood rankings, degrading severely under strong LDP noise and data heterogeneity. We present Gravitational Federated Clustering (GFC), a novel approach to privacy-preserving federated clustering that overcomes the limitations of distance-based methods under varying LDP. Addressing the critical challenge of clustering non-IID data with diverse privacy guarantees, GFC transforms privatized client centroids into a global gravitational potential field where true cluster centers emerge as topologically persistent singularities. Our framework introduces two key innovations: (1) a client-side compactness-aware perturbation mechanism that encodes local cluster geometry as "mass" values, and (2) a server-side topological aggregation phase that extracts stable centroids through persistent homology analysis of the potential field's superlevel sets. Theoretically, we establish a closed-form bound between the privacy budget ε and centroid estimation error, proving the potential field's Lipschitz smoothing properties exponentially suppress noise in high-density regions. Empirically, GFC outperforms state-of-the-art methods on ten benchmarks, especially under strong LDP constraints (ε < 1), while maintaining comparable performance at lower privacy budgets. By reformulating federated clustering as a topological persistence problem in a synthetic physics-inspired space, GFC achieves unprecedented privacy-accuracy trade-offs without iterative communication, providing a new perspective for privacy-preserving distributed learning.

Jiahuan Long, Tingsong Jiang, Wen Yao, Yizhe Xiong, Zhengqin Xu, Shuai Jia, Hanqing Liu, Chao Ma

Vision foundation models (VFMs) have demonstrated remarkable capabilities in learning universal visual representations. However, adapting these models to downstream tasks conventionally requires parameter updates, with even parameter-efficient fine-tuning methods necessitating the modification of thousands to millions of weights. In this paper, we investigate the redundancies in the segment anything model (SAM) and then propose a novel parameter-free fine-tuning method. Unlike traditional fine-tuning methods that adjust parameters, our method emphasizes selecting, reusing, and enhancing pre-trained features, offering a new perspective on fine-tuning foundation models. Specifically, we introduce a channel selection algorithm based on the model's output difference to identify redundant and effective channels. By selectively replacing the redundant channels with more effective ones, we filter out less useful features and reuse more task-irrelevant features to downstream tasks, thereby enhancing the task-specific feature representation. Experiments on both out-of-domain and in-domain datasets demonstrate the efficiency and effectiveness of our method in different vision tasks (e.g., image segmentation, depth estimation and image classification). Notably, our approach can seamlessly integrate with existing fine-tuning strategies (e.g., LoRA, Adapter), further boosting the performance of already fine-tuned models. Moreover, since our channel selection involves only model inference, our method significantly reduces GPU memory overhead.

Ziwei Liu, Borui Kang, Wei Li, Hangjie Yuan, Yanbing Yang, Wenbin Li, Yifan Zhu, Tao Feng, Jun Luo

Vision-Language Continual Learning (VLCL) has attracted significant research attention for its robust capabilities, and the adoption of Parameter-Efficient Fine-Tuning (PEFT) strategies is enabling these models to achieve competitive performance with substantially reduced resource consumption. However, dominated First-Order (FO) optimization is prone to trap models in suboptimal local minima, especially in limited exploration subspace within PEFT. To overcome this challenge, this paper pioneers a systematic exploration of adopting Zeroth-Order (ZO) optimization for PEFT-based VLCL. We first identify the incompatibility of naive full-ZO adoption in VLCL due to optimization process instability. We then investigate the application of ZO optimization from a modality branch-wise to a fine-grained layer-wise across various training units to identify an optimal strategy. Besides, a key theoretical insight reveals that vision modality exhibit higher variance than language counterparts in VLCL during the ZO optimization process, and we propose a modality-aware stabilized ZO strategy, which adopts gradient sign normalization in ZO and constrains vision modality perturbation to further improve performance. Benefiting from the adoption of ZO optimization, PEFT-based VLCL fulfills better ability to escape local minima during the optimization process, extensive experiments on four benchmarks demonstrate that our method achieves state-of-the-art results.

Ziheng Liu, Jiayi Zhang, Haoyu Wang, Bokai Xu, Chen Zhang, Yiyang Zhu, Enyu Shi

Emerging from recent advances in foundation models, Large Wireless Models (LWMs) represent a new paradigm of general-purpose intelligence for wireless communications that transcends task-specific engineering. The success of foundation models is critically underpinned by scaling laws, which provide a predictable roadmap for how performance scales with resources. However, established scaling laws from language and vision, charting performance as a power-law of model and dataset sizes, are ill-suited for the wireless domain, as their core formulations cannot model the structured nature of the physical channel. To address this, we propose a novel wireless scaling law that extends the classical formulation by modeling two wireless-native factors: channel heterogeneity and discretization granularity. These two factors reshape scaling behavior via nested linear and power-law relationships, recasting the scaling law's parameters (notably the scaling exponent and irreducible loss) from universal constants into dynamic variables dictated by the physical environment. Our physics-aware formulation reveals two key insights: first, that compute-optimal scaling is not dictated by a fixed model-data ratio but is instead a dynamic function of heterogeneity and granularity, and second, that this dependency is particularly sensitive to granularity, allowing significant performance to be unlocked from existing data simply by refining its resolution. Crucially, this establishes a reliable roadmap for designing powerful yet resource-efficient LWMs, translating theoretical insights into actionable engineering principles. Extensive experiments validate our wireless scaling law, showing a 32.31% prediction accuracy improvement over classical laws in diverse wireless scenarios where they fail.

Zhuoyao Liu, Yang Liu, Wentao Feng, Shudong Huang

Cross-modal retrieval aims to align different modalities via semantic similarity. However, existing methods often assume that image-text pairs are perfectly aligned, overlooking Noisy Correspondences in real data. These misaligned pairs misguide similarity learning and degrade retrieval performance. Previous methods often rely on coarse-grained categorizations that simply divide data into clean and noisy samples, overlooking the intrinsic diversity within noisy instances. Moreover, they typically apply uniform training strategies regardless of sample characteristics, resulting in suboptimal sample utilization for model optimization. To address the above challenges, we introduce a novel framework, called Pseudo-label Consistency-Guided Sample Refinement (PCSR), which enhances correspondence reliability by explicitly dividing samples based on pseudo-label consistency. Specifically, we first employ a confidence-based estimation to distinguish clean and noisy pairs, then refine the noisy pairs via pseudo-label consistency to uncover structurally distinct subsets. We further proposed a Pseudo-label Consistency Score (PCS) to quantify prediction stability, enabling the separation of ambiguous and refinable samples within noisy pairs. Accordingly, we adopt Adaptive Pair Optimization (APO), where ambiguous samples are optimized with robust loss functions and refinable ones are enhanced via text replacement during training. Extensive experiments on CC152K, MS-COCO and Flickr30K validate the effectiveness of our method in improving retrieval robustness under noisy supervision.

Zhixin Liu, Xuanlin Liu, Sihan Xu, Yaqiong Qiao, Ying Zhang, Xiangrui Cai

Existing backdoor attacks on multivariate time series (MTS) forecasting enforce strict temporal and dimensional coupling between triggers and target patterns, requiring synchronous activation at fixed positions across variables. However, realistic scenarios often demand delayed and variable-specific activation. We identify this critical unmet need and propose TDBA, a temporally decoupled backdoor attack framework for MTS forecasting. By injecting triggers that encode the expected location of the target pattern, TDBA enables the activation of the target pattern at any positions within the forecasted data, with the activation position flexibly varying across different variable dimensions. TDBA introduces two core modules: (1) a position-guided trigger generation mechanism that leverages smoothed Gaussian priors to generate triggers that are position-related to the predefined target pattern; and (2) a position-aware optimization module that assigns soft weights based on trigger completeness, pattern coverage, and temporal offset, facilitating targeted and stealthy attack optimization. Extensive experiments on real-world datasets show that TDBA consistently outperforms existing baselines in effectiveness while maintaining good stealthiness. Ablation studies confirm the controllability and robustness of its design.

Zhenxian Liu, Peixi Peng, Yangru Huang, Yonghong Tian

World-model-based reinforcement learning achieves high sample efficiency by learning from imagined rollouts. However, its success critically depends on the accuracy of the learned world model, which is prone to producing unrealistic or hallucinated rollouts when queried beyond its domain of competence. These flawed predictions can trap the agent in a vicious cycle: by misleading exploration toward implausible or uninformative regions, they degrade the quality of collected data, which in turn corrupts policy learning with inaccurate rollouts. To break this cycle, we introduce the notion of a knowledge boundary—the region within which the world model provides reliable predictions—and propose a unified framework that both identifies and leverages this boundary. Concretely, we approximate the boundary using model uncertainty, quantified via disagreement across an ensemble of lightweight predictors, which serves as a practical proxy. This uncertainty signal is used in two complementary ways: as an intrinsic reward to guide exploration toward under-explored yet learnable regions, and as a dynamic filter to exclude unreliable imagined rollouts from policy optimization. Extensive experiments across diverse benchmarks—including CARLA, DeepMind Control Suite, Atari, and MemoryMaze—demonstrate that our approach consistently outperforms prior state-of-the-art methods.

Zhenjiao Liu, Xue Xiao, Yao Chen, Jiao Xue, Shubin Ma, Liang Zhao

Multimodal data is typically collected through heterogeneous sensors and processing pipelines. However, due to variations in acquisition environments, device capabilities, and feature extraction methods, such data often suffers from incompleteness and inconsistent quality across modalities. To address these challenges, prior studies have explored modality selection and data completion strategies to improve information fusion. Nevertheless, these approaches face two main limitations: (1) they struggle to simultaneously ensure computational efficiency for large-scale graph data and maintain structural and semantic consistency across heterogeneous modality graphs; and (2) most of them operate at the modality level and fail to capture fine-grained, sample-specific quality variations. To overcome these issues, we propose a novel clustering framework, Sample Weighted Incomplete Multimodal Clustering Based on Graph Coarsening Label Extraction (IMC-GCSW). The proposed method introduces a graph coarsening-based label extraction strategy. It significantly reduces the computational cost of multimodal graph processing, while preserving key node information and local topological structures. Furthermore, a quality-aware sample weighting strategy is designed to enable fine-grained modeling of modality-specific data quality, allowing the model to dynamically suppress the influence of low-quality modalities on individual samples. Experiments on both general-purpose datasets and the Fructus Aurantii Disease and Pest Datasets demonstrate that the proposed method exhibits superior performance and strong adaptability in handling multimodal data with incompleteness and quality inconsistency.

Zhen Liu, Yucheng Wang, Boyuan Li, Junhao Zheng, Emadeldeen Eldele, Min Wu, Qianli Ma

Foundation models pre-trained on large-scale source datasets are reshaping the traditional training paradigm for time series classification. However, existing time series foundation models primarily focus on forecasting tasks and often overlook classification-specific challenges, such as modeling interpretable shapelets that capture class-discriminative temporal features. To bridge this gap, we propose UniShape, a unified shape-aware foundation model designed for time series classification. UniShape incorporates a shape-aware adapter that adaptively aggregates multiscale discriminative subsequences (shapes) into class tokens, effectively selecting the most relevant subsequence scales to enhance model interpretability. Meanwhile, a prototype-based pretraining module is introduced to jointly learn instance- and shape-level representations, enabling the capture of transferable shape patterns. Pre-trained on a large-scale multi-domain time series dataset comprising 1.89 million samples, UniShape exhibits superior generalization across diverse target domains. Experiments on 128 UCR datasets and 30 additional time series datasets demonstrate that UniShape achieves state-of-the-art classification performance, with interpretability and ablation analyses further validating its effectiveness.

Zhaowei Liu, Yihao Jiang, Rufei Gao, Jinglei Liu, Dong Yang

Graph Neural Networks (GNNs) have demonstrated superior performance in processing centralized graph-structured data. However, real-world privacy and security concerns hinder data centralization and shareing, leading to severe data isolation (data silos). While Federated Learning (FL) offers a distributed solution to mitigate these obstacles, existing Federated Graph Neural Network (FedGNN) frameworks struggle to effectively address data heterogeneity. To address this, this paper proposes DA-DFGAS, a federated graph neural architecture search algorithm. Specifically, DA-DFGAS facilitates model personalization via a directed tree topology and path constraint mechanisms, while simultaneously employing a joint self-attention mechanism based on predicted probability distributions to capture distributional variations across multiple clients. Furthermore, it integrates a bi-level global-local objective optimization strategy to ensure global model consistency while preserving local adaptability. Experimental results on multiple datasets demonstrate that DA-DFGAS outperforms state-of-the-art methods, achieving 0.5–3.0% accuracy improvements over centralized baselines and 0.5–5.0% over federated counterparts.

Zehao Liu, Kun Li, Wei Zhou

Model merging serves as a training-free technique that combines multiple task-specific models into a unified multi-task model, but parameter conflicts often lead to performance drops. Previous methods flatten weight matrices into one-dimensional vectors, losing the inherent structural information of their row and column spaces. We mathematically prove and experimentally validate that parameter conflicts arise from non-orthogonal components of task vectors, while orthogonal components are conflict-free. Furthermore, we find that non-orthogonal components can contain both harmful conflicts and beneficial synergies. To precisely locate parameter conflicts and extract orthogonal components, we propose GLOBA (GLObal Basis Analysis Framework), which projects task vectors onto a global basis to align them within a unified coordinate system and construct a task interaction matrix. Following energy-based pruning, we divide parameters into five types based on the orthogonal relationships between the row spaces and column spaces of task vectors. Experiments on three fine-tuned models (mathematics, coding, and instruction-following) using LLaMA-2-7B and LLaMA-2-13B demonstrate significant performance gains through selective retention of beneficial parameters and removal of conflicting ones.

Yuzhou Liu, Jiarui Liu, Wanfu Gao

Multi-view multi-label data offers richer perspectives for artificial intelligence, but simultaneously presents significant challenges for feature selection due to the inherent complexity of interrelations among features, views and labels. Attention mechanisms provide an effective way for analyzing these intricate relationships. They can compute importance weights for information by aggregating correlations between Query and Key matrices to focus on pertinent Values. However, existing attention-based feature selection methods predominantly focus on intra-view relationships, neglecting the complementarity of inter-view features and the critical feature-label correlations. Moreover, they often fail to account for feature redundancy, potentially leading to suboptimal feature subsets. To overcome these limitations, we propose a novel method based on Redundancy-optimized Multi-head Attention Networks for Multi-view Multi-label Feature Selection (RMAN-MMFS). Specifically, we employ each individual attention head to model intra-view feature relationships and use the cross-attention mechanisms between different heads to capture inter-view feature complementarity. Furthermore, we design static and dynamic feature redundancy terms: the static term mitigates redundancy within each view, while the dynamic term explicitly models redundancy between unselected and selected features across the entire selection process, thereby promoting feature compactness. Comprehensive evaluations on six real-world datasets, comparing against six multi-view multi-label feature selection methods, demonstrate the superior performance of the proposed method.

Yuze Liu, Chaochao Lu, Chao Yang

Reinforcement learning (RL) has emerged as the predominant paradigm for training large language model (LLM) agents to solve complex, multi-step tasks through environmental interaction. A fundamental challenge in such long-horizon scenarios is credit assignment, as delayed rewards provide inadequate signals for evaluating individual action contributions. Existing methods typically neglect trajectory transition dynamics, which leads to coarse-grained or biased credit assignment. To address these limitations, we introduce SHADOW, a novel framework that systematically incorporates transition dynamics for improved credit assignment. Our framework makes two primary contributions: (i) a dynamics-aware state grouping mechanism that mitigates misleading action comparisons between dynamically inconsistent states, and (ii) a local dynamic advantage estimator that leverages Generalized Advantage Estimation (GAE) to precisely quantify individual action contributions through a fine-grained analysis of transition patterns. Comprehensive experiments conducted with the Qwen2.5-1.5/7B-Instruct agent model demonstrate that our method achieves success rate improvements of 9.4%/7.6% on the ALFworld benchmark and a performance gain of over 5% on WebShop.

Yuxuan Liu, Wenchao Xu, Haozhao Wang, Zhiming He, Zhaofeng Shi, Chongyang Xu, Peichao Wang, Boyuan Zhang

Federated Graph Learning (FGL) has emerged as a powerful paradigm for decentralized training of graph neural networks while preserving data privacy. However, existing FGL methods are predominantly designed for static graphs and rely on parameter averaging or distribution alignment, which implicitly assume that all features are equally transferable across clients, overlooking both the spatial and temporal heterogeneity and the presence of client-specific knowledge in real-world graphs. In this work, we identify that such assumptions create a vicious cycle of spurious representation entanglement, client-specific interference, and negative transfer, degrading generalization performance in Federated Learning over Dynamic Spatio-Temporal Graphs (FSTG). To address this issue, we propose a novel causality-inspired framework named SC-FSGL, which explicitly decouples transferable causal knowledge from client-specific noise through representation-level interventions. Specifically, we introduce a Conditional Separation Module that simulates soft interventions through client conditioned masks, enabling the disentanglement of invariant spatio-temporal causal factors from spurious signals and mitigating representation entanglement caused by client heterogeneity. In addition, we propose a Causal Codebook that clusters causal prototypes and aligns local representations via contrastive learning, promoting cross-client consistency and facilitating knowledge sharing across diverse spatio-temporal patterns. Experiments on five diverse heterogeneity Spatio-Temporal Graph (STG) datasets show that SC-FSGL outperforms state-of-the-art methods.

Yu Liu, Haoqin Yang, Jinping Sui, Hui Wang, Haipeng Li, Weimin Wang, Qi Jia

Class-incremental learning (CIL) has recently gained great attention in the field of time series classification. Existing CIL methods based on knowledge distillation exhibit impressive ability to retain prior knowledge and overcome catastrophic forgetting, however, their effectiveness faces major challenges posed by time series data. Since temporal data is more susceptible to sensor errors and electronic noise, the distillation process may be significantly affected by noisy knowledge transfer. To address this issue, we propose a novel confidence-guided mask distillation (CMD) framework, to prevent the noisy inheritance during distillation. The core of CMD lies in a dynamic masking mechanism guided by prediction confidence, capable of allocating higher weights to high-confidence time series and substantially suppressing the influence of low-confidence ones. Additionally, different from prior work simply passing a set of feature prototypes to the classifier, we develop prototype-guided contrastive learning (PCL) to alleviate the classifier bias on new classes, through extra contrastive constraints to push away the feature distributions of old feature prototypes from those of new classes features. Extensive experiments on three time-series datasets demonstrate that, our method significantly outperforms other replay-free CIL approaches in raising average accuracy, as well as decreasing forgetting rate.