Author name cluster

Yuxin Wu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

11 papers

2 author rows

AAAI Conference 2026 Conference Paper

ST-TPP: Learning Semi-Transductive Temporal Point Processes with Gromov-Wasserstein Barycentric Regularization

Qingmei Wang
Tianyu Huang
Yujie Long
Yuxin Wu
Fanmeng Wang
Xi Sun
Junchi Yan
Hongteng Xu

The generative mechanisms behind real-world event sequences are often heterogeneous, leading to data that possesses inherent clustering structures. However, most existing temporal point processes (TPPs) treat different event sequences independently, without leveraging the clustering structures when predicting events. In this study, we design and learn a novel semi-transductive temporal point process (ST-TPP), which explicitly improves prediction performance by co-training sequence clusters. In particular, given a set of event sequences, our method learns a neural TPP together with cluster centers of the sequences. Besides maximizing the likelihood of the event sequences, we leverage a data-based kernel matrix and prior knowledge to regularize the sequence embeddings, leading to a Gromov-Wasserstein barycentric (GWB) regularizer. Based on the optimal transport plans associated with the GWB regularizer, we derive the cluster centers by the push-forward of the sequence embeddings. When a new sequence comes, the learned model first assigns a cluster center to the sequence and then jointly encodes the sequence and the cluster center to predict future events, leading to a semi-transductive prediction scheme. Experiments demonstrate that ST-TPP achieves competitive sequence clustering results and strong prediction performance.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Towards Robust Text-Attributed Federated Graph Learning: Multimodal Threats and Defense

Zitong Shi
Guancheng Wan
Wenke Huang
Yuxin Wu
Quan Zhang
Mang Ye

Text-Attributed Graphs (TAGs) are graphs where both nodes and edges are associated with text attributes. To leverage their semantic richness, recent efforts have integrated large language models (LLMs) with graph neural networks, leading to the development of GraphLLMs. However, many real-world datasets remain inaccessible, and processing text-attributed graphs while ensuring privacy and efficiency remains a challenge. To address this, we place TAGs within a federated environment, referred to as TAG-FGL. Despite its potential, TAG-FGL remains largely underexplored in the face of adversarial threats. In this work, we introduce GTAE, a novel attack framework that cascades influence-guided topological perturbations and embedding-level text refinements to generate transferable, modality-agnostic adversarial inputs. To defend against these threats, we propose STRUM, a defense strategy that combines local adversarial training with robustness-aware aggregation, enhancing resilience at both the node and system levels. Extensive experiments on five real-world datasets with diverse model backbones demonstrate that GTAE significantly degrades model performance, while STRUM consistently improves robustness.

PDF Details DOI

AAAI Conference 2025 Conference Paper

A Plug-and-Play Bregman ADMM Module for Inferring Event Branches in Temporal Point Processes

Qingmei Wang
Yuxin Wu
Yujie Long
Jing Huang
Fengyuan Ran
Bing Su
Hongteng Xu

An event sequence generated by a temporal point process is often associated with a hidden and structured event branching process that captures the triggering relations between its historical and current events. In this study, we design a new plug-and-play module based on the Bregman ADMM (BADMM) algorithm, which infers event branches associated with event sequences in the maximum likelihood estimation framework of temporal point processes (TPPs). Specifically, we formulate the inference of event branches as an optimization problem of event transition matrix under sparse and low-rank constraints, which is embedded in existing TPP models or their learning paradigms. We can implement this optimization problem based on subspace clustering and sparse group-lasso, respectively, and solve it using the Bregman ADMM algorithm, whose unrolling leads to the proposed BADMM module. When learning a classic TPP (e.g., Hawkes process) by the expectation-maximization algorithm, the BADMM module helps derive structured responsibility matrices in the E-step. Similarly, the BADMM module helps derive low-rank and sparse attention maps for the neural TPPs with self-attention layers. The structured responsibility matrices and attention maps, which work as learned event transition matrices, indicate event branches, e.g., inferring isolated events and those key events triggering many subsequent events. Experiments on both synthetic and real-world data show that plugging our BADMM module into existing TPP models and learning paradigms can improve model performance and provide us with interpretable structured event branches.

PDF Details DOI

EAAI Journal 2025 Journal Article

A strongly supervised hyperspectral unmixing framework for precise mineral composition and coal ash content estimation

Yao Cui
Ziqi Lv
Ying Gao
Yuxin Wu
Xuan Zhao
Qingxuan Meng
Jun Dong
Zhiqiang Xu

Accurate coal ash content detection is essential for advancing intelligent clean coal processing and holds significant practical value across mining, washing, combustion, and conversion technologies. This paper introduces a strongly supervised hyperspectral unmixing (SSHU) framework designed to estimate mineral composition proportions and ash content. We conducted systematic ablation experiments on concentrated coal and tailings coal datasets to evaluate the method's effectiveness and analyze the mechanisms of proportional prior information and reconstruction decoders. Results demonstrate that proportional prior information effectively constrains the proportional encoder, making estimated mineral and pure coal distributions closer to actual material distributions. The reconstruction decoder enhances the proportional encoder's feature extraction ability, guides model convergence, and improves both proportion and ash content estimation accuracy. Compared to existing hyperspectral unmixing methods, our approach incorporates pure substance spectral information during model training and combines proportional prior constraints. This provides a robust solution for complex mixture analysis and demonstrates significant potential in hyperspectral unmixing applications.

Details DOI

EAAI Journal 2025 Journal Article

Fault diagnosis of high-voltage three-phase asynchronous motors using residual neural networks and bidirectional gated recurrent units

Huihui Yang
Yuxin Wu

High-voltage three-phase asynchronous motors are extensively used in industrial production; however, rotor bar breakage faults are characterized by strong concealment and severe consequences, making early and accurate diagnosis difficult with traditional methods. To address this issue, this paper proposes a deep learning model based on a Residual Neural Network (ResNet) and a Bidirectional Gated Recurrent Unit (Bi-GRU) for motor fault diagnosis. The proposed model integrates the spatial feature extraction advantages of ResNet with the temporal modeling capabilities of Bi-GRU, simultaneously capturing spatiotemporal information from voltage and current signals. The model was trained and tested on a large-scale dataset comprising 324, 000 data points under nine distinct operating conditions. Experimental results demonstrate that the proposed method achieves over 99. 83 % in key metrics such as accuracy, precision, recall, and F1-score, significantly outperforming traditional approaches and other comparative models. Additionally, it maintains stable performance under varying operating conditions, demonstrating strong robustness and generalization capability. Further ablation experiments also validated the effectiveness of each module within the proposed model. This study indicates that the application of deep learning in industrial motor fault diagnosis has promising prospects and practical value.

Details DOI

ICML Conference 2025 Conference Paper

GHOST: Generalizable One-Shot Federated Graph Learning with Proxy-Based Topology Knowledge Retention

Jiaru Qian
Guancheng Wan
Wenke Huang 0003
Guibin Zhang
Yuxin Wu
Bo Du 0001
Mang Ye

Federated Graph Learning (FGL) proposes an effective approach to collaboratively training Graph Neural Networks (GNNs) while maintaining privacy. Nevertheless, communication efficiency becomes a critical bottleneck in environments with limited resources. In this context, one-shot FGL emerges as a promising solution by restricting communication to a single round. However, prevailing FGL methods face two key challenges in the one-shot setting: 1) They heavily rely on gradual personalized optimization over multiple rounds, undermining the capability of the global model to efficiently generalize across diverse graph structures. 2) They are prone to overfitting to local data distributions due to extreme structural bias, leading to catastrophic forgetting. To address these issues, we introduce GHOST, an innovative one-shot FGL framework. In GHOST, we establish a proxy model for each client to leverage diverse local knowledge and integrate it to train the global model. During training, we identify and consolidate parameters essential for capturing topological knowledge, thereby mitigating catastrophic forgetting. Extensive experiments on real-world tasks demonstrate the superiority and generalization capability of GHOST. The code is available at https: //github. com/JiaruQian/GHOST.

Details

NeurIPS Conference 2025 Conference Paper

HYPERION: Fine-Grained Hypersphere Alignment for Robust Federated Graph Learning

Frank Wan
Xiaoran Shang
Yuxin Wu
Guibin Zhang
Jinhe Bi
Liangtao Zheng
Xin Lin
Yue Liu

Robust Federated Graph Learning (FGL) provides an effective decentralized framework for training Graph Neural Networks (GNNs) in noisy-label environments. However, the subtlety of noise during training presents formidable obstacles for developing robust FGL systems. Previous robust FL approaches neither adequately constrain edge-mediated error propagation nor account for intra-class topological differences. At the client level, we innovatively demonstrate that hyperspherical embedding can effectively capture graph structures in a fine-grained manner. Correspondingly, our method effectively addresses the aforementioned issues through fine-grained hypersphere alignment. Moreover, we uncover undetected noise arising from localized perspective constraints and propose the geometric-aware hyperspherical purification module at the server level. Combining both level strategies, we present our robust FGL framework, **HYPERION**, which operates all components within a unified hyperspherical space. **HYPERION** demonstrates remarkable robustness across multiple datasets, for instance, achieving a 29. 7\% $\uparrow$ F1-macro score with 50\%-pair noise on Cora. The code is available for anonymous access at \url{https: //anonymous. 4open. science/r/Hyperion-NeurIPS/}.

PDF Details

NeurIPS Conference 2025 Conference Paper

MoBA: Mixture of Block Attention for Long-Context LLMs

Enzhe Lu
Zhejun Jiang
Jingyuan Liu
Yulun Du
Tao Jiang
Chao Hong
Shaowei Liu
Weiran He

Scaling the effective context length is essential for advancing large language models (LLMs) toward artificial general intelligence (AGI). However, the quadratic increase in computational complexity inherent in traditional attention mechanisms presents a prohibitive overhead. Existing approaches either impose strongly biased structures, such as sink or window attention which are task-specific, or radically modify the attention mechanism into linear approximations, whose performance in complex reasoning tasks remains inadequately explored. In this work, we propose a solution that adheres to the ``less structure'' principle, allowing the model to determine where to attend autonomously, rather than introducing predefined biases. We introduce Mixture of Block Attention (MoBA), an innovative approach that applies the principles of Mixture of Experts (MoE) to the attention mechanism. This novel architecture demonstrates superior performance on long-context tasks while offering a key advantage: the ability to seamlessly transition between full and sparse attention, enhancing efficiency without the risk of compromising performance. MoBA has already been deployed to handle actual production workloads with long-context requirements, demonstrating significant advancements in efficient attention computation for LLMs. Our code is available at https: //github. com/MoonshotAI/MoBA.

PDF Details

NeurIPS Conference 2025 Conference Paper

MOTION: Multi-Sculpt Evolutionary Coarsening for Federated Continual Graph Learning

Frank Wan
Fengyuan Ran
Ruikang Zhang
Wenke Huang
Xuankun Rong
Guibin Zhang
Yuxin Wu
Bo Du

Graph neural networks (GNNs) have achieved remarkable success in various domains but typically rely on centralized, static graphs, which limits their applicability in distributed, evolving environments. To address this limitation, we define the task of Federated Continual Graph Learning (FCGL), a paradigm for incremental learning on dynamic graphs distributed across decentralized clients. Existing methods, however, neither preserve graph topology during task transitions nor mitigate parameter conflicts in server‐side aggregation. To overcome these challenges, we introduce **MOTION**, a generalizable FCGL framework that integrates two complementary modules: the Graph Topology‐preserving Multi‐Sculpt Coarsening (G‐TMSC) module, which maintains the structural integrity of past graphs through a multi‐expert, similarity‐guided fusion process, and the Graph‐Aware Evolving Parameter Adaptive Engine (G‐EPAE) module, which refines global model updates by leveraging a topology‐sensitive compatibility matrix. Extensive experiments on real‐world datasets show that our approach improves average accuracy (AA) by an average of 30\% $\uparrow$ over the FedAvg baseline across five datasets while maintaining a negative $\downarrow$ average forgetting (AF) rate, significantly enhancing generalization and robustness under FCGL settings. The code is available for anonymous access at https: //anonymous. 4open. science/r/MOTION.

PDF Details

JBHI Journal 2024 Journal Article

Scoring Aided Federated Learning on Long-Tailed Data for Wireless IoMT Based Healthcare System

Lianhong Zhang
Yuxin Wu
Lunyuan Chen
Lisheng Fan
Arumugam Nallanathan

In this article, we propose a novel federated learning (FL) framework for wireless Internet of Medical Things (IoMT) based healthcare systems, where multiple mobile clients and one edge server (ES) collaboratively train a shared model on long-tail data through wireless channels. However, the presence of long-tailed data in this system may introduce a biased global model which fails to handle the tail classes. Additionally, the occurrence of severe fading in wireless channels may prevent mobile clients from successfully uploading local models to the ES, thereby excluding them from participating in the model aggregation. These situations adversely affect the performance of FL. To overcome these challenges, we propose a novel scoring aided FL framework that uses a scoring-based sampling strategy to select mobile clients with more tailed data and better transmission conditions to upload their local models. Specifically, we leverage the logits to explore the data distribution among local clients and propose a logits based scoring client selection method to alleviate the impact of long-tailed data. Moreover, we address the impact of severe fading by incorporating the channel state information (CSI) and data rate of clients into the logits based scoring and proposing a novel logits and model upload rate based client selection method. Experimental results demonstrate the effectiveness of our proposed framework. In particular, compared to the conventional FedAvg, the proposed framework can achieve accuracy gains ranging from 4. 44% to 28. 36% on the CIFAR-10-LT dataset with an imbalance factor (IF) of 50.

Details DOI

NeurIPS Conference 2017 Conference Paper

ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games

Yuandong Tian
Qucheng Gong
Wenling Shang
Yuxin Wu
C. Lawrence Zitnick

In this paper, we propose ELF, an Extensive, Lightweight and Flexible platform for fundamental reinforcement learning research. Using ELF, we implement a highly customizable real-time strategy (RTS) engine with three game environments (Mini-RTS, Capture the Flag and Tower Defense). Mini-RTS, as a miniature version of StarCraft, captures key game dynamics and runs at 165K frame-per-second (FPS) on a laptop. When coupled with modern reinforcement learning methods, the system can train a full-game bot against built-in AIs end-to-end in one day with 6 CPUs and 1 GPU. In addition, our platform is flexible in terms of environment-agent communication topologies, choices of RL methods, changes in game parameters, and can host existing C/C++-based game environments like ALE. Using ELF, we thoroughly explore training parameters and show that a network with Leaky ReLU and Batch Normalization coupled with long-horizon training and progressive curriculum beats the rule-based built-in AI more than 70% of the time in the full game of Mini-RTS. Strong performance is also achieved on the other two games. In game replays, we show our agents learn interesting strategies. ELF, along with its RL platform, is open-sourced at https: //github. com/facebookresearch/ELF.

PDF Details