Arrow Research search

Author name cluster

Guancheng Wan

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.

26 papers
2 author rows

Possible papers

26

AAAI Conference 2026 Conference Paper

DAWN: Distributed LLM Multi-Agent Workflow Synthesis

  • Guancheng Wan
  • Mo Zhou
  • Ziyi Wang
  • Xiaoran Shang
  • Eric Hanchen Jiang
  • Guibin Zhang
  • Jinhe Bi
  • Yunpu Ma

Large language models (LLMs) have recently empowered multi-agent systems (MAS) to achieve remarkable advances in collaborative reasoning and complex task automation. The effectiveness of these systems fundamentally depends on the design of adaptive communication graphs—the underlying workflows that coordinate agent interactions. However, in real-world scenarios, strict privacy constraints often silo data across organizations, and client distributions are highly non-IID, posing major challenges for synthesizing such workflows. In this work, we are the first to systematically study distributed multi-agent workflow synthesis under these privacy and heterogeneity constraints, and we introduce the Difficulty-Based Skew (DBS) benchmark to emulate such challenging environments. Drawing inspiration from federated graph learning (FGL)—which has primarily focused on classification over static graphs—we identify a critical gap: existing FGL methods do not address the generative design of communication topologies. We reveal two fundamental obstacles to generative workflow synthesis in this setting: (i) workflow specialization conflict, where agents optimized for different task distributions generate incompatible communication patterns that resist meaningful aggregation, and (ii) structural communication shift, where locally optimal agent interaction graphs fail to compose into globally coherent multi-agent workflows. To address these challenges, we propose DAWN, a federated framework that integrates two key innovations: Parametric Resonance, which robustly aggregates heterogeneous local updates via layer-wise SVD-based denoising and alignment, and Structural Gravity, which regularizes local workflow generation by penalizing the Fusion Gromov-Wasserstein distance to a set of prototype communication graphs, ensuring global structural coherence without stifling local adaptation. Experiments on the DBS benchmark show that DAWN surpasses baselines in global task success and reduces inter-client graph divergence, laying a solid foundation for privacy-preserving, adaptive MAS workflow design in heterogeneous settings.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Segmentation

  • Xingyue Zhao
  • Wenke Huang
  • Xingguang Wang
  • Haoyu Zhao
  • Linghao Zhuang
  • Anwen Jiang
  • Guancheng Wan
  • Mang Ye

Federated learning enables multiple medical institutions to train a global model without sharing data, yet feature heterogeneity from diverse scanners or protocols remains a major challenge. Many existing works attempt to address this issue by leveraging model representations (e.g., mean feature vectors) to correct local training; however, they often face two key limitations: 1) Incomplete Contextual Representation Learning: Current approaches primarily focus on final-layer features, overlooking critical multi-level cues and thus diluting essential context for accurate segmentation. 2) Layerwise Style Bias Accumulation: Although utilizing representations can partially align global features, these methods neglect domain-specific biases within intermediate layers, allowing style discrepancies to build up and reduce model robustness. To address these challenges, we propose FedBCS to bridge feature representation gaps via domain-invariant contextual prototypes alignment. Specifically, we introduce a frequency-domain adaptive style recalibration into prototype construction that not only decouples content-style representations but also learns optimal style parameters, enabling more robust domain-invariant prototypes. Furthermore, we design a context-aware dual-level prototype alignment method that extracts domain-invariant prototypes from different layers of both encoder and decoder and fuses them with contextual information for finer-grained representation alignment. Extensive experiments on two public datasets demonstrate that our method exhibits remarkable performance.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Domain-Aware Suppression and Aggregation for Federated DG ReID

  • Zhixi Yu
  • Wei Liu
  • Wenke Huang
  • Bin Yang
  • Qian Bie
  • Guancheng Wan
  • Xin Xu

Federated domain generalization in person re-identification (FedDG-ReID) aims to learn a privacy-preserving server model from decentralized client source domains that generalizes to unseen domains. Existing approaches enhance the generalizability of the server model by increasing the diversity of client person data. However, these methods overlook that ReID model parameters are easily biased by client-specific data distributions, leading to the capture of excessive domain-specific identity information. Such identity information (e.g., clothing style) struggles with identity information in unseen domains, thereby hindering the generalization ability of the server model. To address this, we propose a novel FedDG-ReID framework, which mainly consists of Domain-aware Parameter Suppression (DPS) and Domain-invariant Weighted Aggregation (DWA), called FedSupWA. Specifically, DPS adaptively attenuates the update magnitude of the parameters based on the fit of the parameters to the client's domain, encouraging the model to focus on more generalized domain-independent identity information, such as pedestrian contours, and other consistent information across domains. DWA enhances the server model’s generalization by evaluating the effectiveness of the client model in maintaining the consistency of pedestrian identities to measure the importance of the learned domain-independent identity information and assigning greater aggregation weights to clients that contribute more generalized information. Extensive experiments demonstrate the effectiveness of FedSupWA, showing that it achieves state-of-the-art performance.

PDF Details DOI

AAAI Conference 2026 Conference Paper

PurMM: Attention-Guided Test-Time Backdoor Purification in Multimodal Large Language Models

  • Wenzheng Jiang
  • Ke Liang
  • Xuankun Rong
  • Jingxuan Zhou
  • Zhengyi Zhong
  • Guancheng Wan
  • Ji Wang

Downstream fine-tuning of Multimodal Large Language Models (MLLMs) is advancing rapidly, allowing general models to achieve superior performance on domain-specific tasks. Yet most prior research focuses on performance gains and overlooks the vulnerability of the fine-tuning pipeline: attackers can easily poison the dataset to implant backdoors into MLLMs. We conduct an in-depth investigation of backdoor attacks on MLLMs and reveal the phenomenon of Attention Hijacking and its Hierarchical Mechanism. Guided by this insight, we propose PurMM, a test-time backdoor purification framework that removes visual tokens exhibiting anomalous attention, thereby avoiding targeted outputs while restoring correct answers. PurMM contains three stages: (1) locating tokens with abnormal attention, (2) filtering them using deep-layer cues, and (3) zeroing out their corresponding components in the visual embeddings. Unlike existing defences, PurMM dispenses with retraining and training-process modifications, operating at test-time to restore model performance while eliminating the backdoor. Extensive experiments across multiple MLLMs and datasets show that PurMM maintains normal performance, sharply reduces attack success rates, and consistently converts backdoor outputs to benign ones, offering a new perspective for safeguarding MLLMs.

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

IJCAI Conference 2025 Conference Paper

An Empirical Study of Federated Prompt Learning for Vision Language Model

  • Zhihao Wang
  • Wenke Huang
  • Tian Chen
  • Zekun Shi
  • Guancheng Wan
  • Yu Qiao
  • Bin Yang
  • Jian Wang

The Vision Language Model (VLM) excels in aligning vision and language representations, and prompt learning has emerged as a key technique for adapting such models to downstream tasks. However, the application of prompt learning with VLM in federated learning (FL) scenarios remains underexplored. This paper systematically investigates the behavioral differences between language prompt learning (LPT) and vision prompt learning (VPT) under data heterogeneity challenges, including label skew and domain shift. We conduct extensive experiments to evaluate the impact of various FL and prompt configurations, such as client scale, aggregation strategies, and prompt length, to assess the robustness of Federated Prompt Learning (FPL). Furthermore, we explore strategies for enhancing prompt learning in complex scenarios where label skew and domain shift coexist, including leveraging both prompt types when computational resources allow. Our findings offer practical insights into optimizing prompt learning in federated settings, contributing to the broader deployment of VLMs in privacy-preserving environments.

PDF Details DOI

ICML Conference 2025 Conference Paper

Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning

  • Wenke Huang 0003
  • Jian Liang 0003
  • Guancheng Wan
  • Didi Zhu
  • He Li 0054
  • Jiawei Shao
  • Mang Ye
  • Bo Du 0001

Fine-tuning Multimodal Large Language Models (MLLMs) in multi-task learning scenarios has emerged as an effective strategy for achieving cross-domain specialization. However, multi-task fine-tuning frequently induces performance degradation on open-response datasets. We posit that free-form answer generation primarily depends on language priors, and strengthening the integration of visual behavioral cues is critical for enhancing prediction robustness. In this work, we propose Noise Resilient Confidence Alignment to address the challenge of open-response overfitting during multi-task fine-tuning. Our approach prioritizes maintaining consistent prediction patterns in MLLMs across varying visual input qualities. To achieve this, we employ Gaussian perturbations to synthesize distorted visual inputs and enforce token prediction confidence alignment towards the normal visual branch. By explicitly linking confidence calibration to visual robustness, this method reduces over-reliance on language priors. We conduct extensive empirical evaluations across diverse multi-task downstream settings via popular MLLM architectures. The comprehensive experiment demonstrates the effectiveness of our method, showcasing its ability to alleviate open-response overfitting while maintaining satisfying multi-task fine-tuning performance.

Details

ICLR Conference 2025 Conference Paper

Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems

  • Guibin Zhang
  • Yanwei Yue
  • Zhixun Li
  • Sukwon Yun
  • Guancheng Wan
  • Kun Wang 0056
  • Dawei Cheng
  • Jeffrey Xu Yu

Recent advancements in large language model (LLM)-powered agents have shown that collective intelligence can significantly outperform individual capabilities, largely attributed to the meticulously designed inter-agent communication topologies. Though impressive in performance, existing multi-agent pipelines inherently introduce substantial token overhead, as well as increased economic costs, which pose challenges for their large-scale deployments. In response to this challenge, we propose an economical, simple, and robust multi-agent communication framework, termed $\texttt{AgentPrune}$, which can seamlessly integrate into mainstream multi-agent systems and prunes redundant or even malicious communication messages. Technically, $\texttt{AgentPrune}$ is the first to identify and formally define the $\textit{Communication Redundancy}$ issue present in current LLM-based multi-agent pipelines, and efficiently performs one-shot pruning on the spatial-temporal message-passing graph, yielding a token-economic and high-performing communication topology. Extensive experiments across six benchmarks demonstrate that $\texttt{AgentPrune}$ $\textbf{(I)}$ achieves comparable results as state-of-the-art topologies at merely $\\$5.6$ cost compared to their $\\$43.7$, $\textbf{(II)}$ integrates seamlessly into existing multi-agent frameworks with $28.1\\%\sim72.8\\%\downarrow$ token reduction, and $\textbf{(III)}$ successfully defend against two types of agent-based adversarial attacks with $3.5\\%\sim10.8\\%\uparrow$ performance boost. The source code is available at \url{https://github.com/yanweiyue/AgentPrune}.

Details

ICML Conference 2025 Conference Paper

Does One-shot Give the Best Shot? Mitigating Model Inconsistency in One-shot Federated Learning

  • Hui Zeng
  • Wenke Huang 0003
  • Tongqing Zhou
  • Xinyi Wu
  • Guancheng Wan
  • Yingwen Chen 0001
  • Zhiping Cai

Turning the multi-round vanilla Federated Learning into one-shot FL (OFL) significantly reduces the communication burden and makes a big leap toward practical deployment. However, this work empirically and theoretically unravels that existing OFL falls into a garbage (inconsistent one-shot local models) in and garbage (degraded global model) out pitfall. The inconsistency manifests as divergent feature representations and sample predictions. This work presents a novel OFL framework FAFI that enhances the one-shot training on the client side to essentially overcome inferior local uploading. Specifically, unsupervised feature alignment and category-wise prototype learning are adopted for clients’ local training to be consistent in representing local samples. On this basis, FAFI uses informativeness-aware feature fusion and prototype aggregation for global inference. Extensive experiments on three datasets demonstrate the effectiveness of FAFI, which facilitates superior performance compared with 11 OFL baselines (+10. 86% accuracy). Code available at https: //github. com/zenghui9977/FAFI_ICML25

Details

ICML Conference 2025 Conference Paper

EAGLES: Towards Effective, Efficient, and Economical Federated Graph Learning via Unified Sparsification

  • Zitong Shi
  • Guancheng Wan
  • Wenke Huang 0003
  • Guibin Zhang
  • He Li 0054
  • Carl Yang 0001
  • Mang Ye

Federated Graph Learning (FGL) has gained significant attention as a privacy-preserving approach to collaborative learning, but the computational demands increase substantially as datasets grow and Graph Neural Network (GNN) layers deepen. To address these challenges, we propose $\textbf{EAGLES}$, a unified sparsification framework. EAGLES applies client-consensus parameter sparsification to generate multiple unbiased subnetworks at varying sparsity levels, reducing the need for iterative adjustments and mitigating performance degradation. In the graph structure domain, we introduced a dual-expert approach: a $\textit{graph sparsification expert}$ uses multi-criteria node-level sparsification, and a $\textit{graph synergy expert}$ integrates contextual node information to produce optimal sparse subgraphs. Furthermore, the framework introduces a novel distance metric that leverages node contextual information to measure structural similarity among clients, fostering effective knowledge sharing. We also introduce the $\textbf{Harmony Sparsification Principle}$, EAGLES balances model performance with lightweight graph and model structures. Extensive experiments demonstrate its superiority, achieving competitive performance on various datasets, such as reducing training FLOPS by 82% $\downarrow$ and communication costs by 80% $\downarrow$ on the ogbn-proteins dataset, while maintaining high performance.

Details

ICML Conference 2025 Conference Paper

EARTH: Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph

  • Guancheng Wan
  • Zewen Liu 0005
  • Xiaojun Shan
  • Max S. Y. Lau
  • B. Aditya Prakash
  • Wei Jin 0009

Effective epidemic forecasting is critical for public health strategies and efficient medical resource allocation, especially in the face of rapidly spreading infectious diseases. However, existing deep-learning methods often overlook the dynamic nature of epidemics and fail to account for the specific mechanisms of disease transmission. In response to these challenges, we introduce an innovative end-to-end framework called Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph (EARTH) in this paper. To learn continuous and regional disease transmission patterns, we first propose EANO, which seamlessly integrates the neural ODE approach with the epidemic mechanism, considering the complex spatial spread process during epidemic evolution. Additionally, we introduce GLTG to model global infection trends and leverage these signals to guide local transmission dynamically. To accommodate both the global coherence of epidemic trends and the local nuances of epidemic transmission patterns, we build a cross-attention approach to fuse the most meaningful information for forecasting. Through the smooth synergy of both components, EARTH offers a more robust and flexible approach to understanding and predicting the spread of infectious diseases. Extensive experiments show EARTH superior performance in forecasting real-world epidemics compared to state-of-the-art methods. The code is available at https: //github. com/GuanchengWan/EARTH.

Details

ICLR Conference 2025 Conference Paper

Energy-based Backdoor Defense Against Federated Graph Learning

  • Guancheng Wan
  • Zitong Shi
  • Wenke Huang 0003
  • Guibin Zhang
  • Dacheng Tao
  • Mang Ye

Federated Graph Learning is rapidly evolving as a privacy-preserving collaborative approach. However, backdoor attacks are increasingly undermining federated systems by injecting carefully designed triggers that lead to the model making incorrect predictions. Trigger structures and injection locations in Federated Graph Learning are more diverse, making traditional federated defense methods less effective. In our work, we propose an effective Federated Graph Backdoor Defense using Topological Graph Energy (FedTGE). At the local client level, it injects distribution knowledge into the local model, assigning low energy to benign samples and high energy to the constructed malicious substitutes, and selects benign clients through clustering. At the global server level, the energy elements uploaded by each client are treated as new nodes to construct a global energy graph for energy propagation, making the selected clients' energy elements more similar and further adjusting the aggregation weights. Our method can handle high data heterogeneity, does not require a validation dataset, and is effective under both small and large malicious proportions. Extensive results on various settings of federated graph scenarios under backdoor attacks validate the effectiveness of this approach.

Details

ICML Conference 2025 Conference Paper

Federated Disentangled Tuning with Textual Prior Decoupling and Visual Dynamic Adaptation

  • Yihao Yang
  • Wenke Huang 0003
  • Guancheng Wan
  • Bin Yang 0026
  • Mang Ye

Federated Parameter-Efficient Fine-Tuning aims to adapt Vision-Language Models for downstream tasks in distributed environments. However, data heterogeneity across participants hinders collaborative effectiveness, necessitating personalized adaptation to cover distinct data distributions. Current personalized methods suffer from two limitations. 1) Textual Property Loss: Existing methods facilitate the collaboration between decoupled prompts at the feature level, which potentially undermines the textual properties of the prompts. 2) Visual Feature Diversity: The diversity of visual features makes it challenging to leverage naive image features directly for image-text alignment in downstream tasks. In this work, we propose Federated Disentangled Tuning with Textual Prior Decoupling and Visual Dynamic Adaptation (FedDDA) to overcome the above limitations. Specifically, we encourage decoupling prompts in a way that maximizes the efficacy of prior knowledge, which is essential for maintaining a coherent linguistic context. Furthermore, we design a visual adaption model to reshape visual space to optimally align with the textual space. Extensive experiments on various image classification tasks show the effectiveness of our work in addressing data heterogeneity. The codes are released at https: //github. com/MoratalYang/FedDDA.

Details

ICML Conference 2025 Conference Paper

FedPHA: Federated Prompt Learning for Heterogeneous Client Adaptation

  • Chengying Fang
  • Wenke Huang 0003
  • Guancheng Wan
  • Yihao Yang
  • Mang Ye

Federated Prompt Learning (FPL) adapts pre-trained Vision-Language Models (VLMs) to federated learning through prompt tuning, leveraging their transferable representations and strong generalization capabilities. Traditional methods often require uniform prompt lengths for federated aggregation, limiting adaptability to clients with diverse prompt lengths and distribution biases. In this paper, we propose Fed erated P rompt Learning for H eterogeneous Client A daptation (FedPHA), a novel framework that combines a fixed-length global prompt for efficient aggregation with local prompts of varying lengths to capture client-specific data characteristics. Additionally, FedPHA designs Singular Value Decomposition (SVD) based projection and bidirectional alignment to disentangle global conflicts arising from client heterogeneity, ensuring that personalized client tasks effectively utilize non-harmful global knowledge. This approach ensures that global knowledge improves model generalization while local knowledge preserves local optimization. Experimental results validate the effectiveness of FedPHA in achieving a balance between global and personalized knowledge in federated learning scenarios.

Details

ICML Conference 2025 Conference Paper

G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks

  • Guibin Zhang
  • Yanwei Yue
  • Xiangguo Sun
  • Guancheng Wan
  • Miao Yu
  • Junfeng Fang
  • Kun Wang 0056
  • Tianlong Chen 0001

Recent advancements in large language model (LLM)-based agents have demonstrated that collective intelligence can significantly surpass the capabilities of individual agents, primarily due to well-crafted inter-agent communication topologies. Despite the diverse and high-performing designs available, practitioners often face confusion when selecting the most effective pipeline for their specific task: Which topology is the best choice for my task, avoiding unnecessary communication token overhead while ensuring high-quality solution? In response to this dilemma, we introduce G-Designer, an adaptive, efficient, and robust solution for multi-agent deployment, which dynamically designs task-aware, customized communication topologies. Specifically, G-Designer models the multi-agent system as a multi-agent network, leveraging a variational graph auto-encoder to encode both the nodes (agents) and a task-specific virtual node, and decodes a task-adaptive and high-performing communication topology. Extensive experiments on six benchmarks showcase that G-Designer is: (1) high-performing, achieving superior results on MMLU with accuracy at $84. 50\%$ and on HumanEval with pass@1 at $89. 90\%$; \textbf{(2) task-adaptive}, architecting communication protocols tailored to task difficulty, reducing token consumption by up to $95. 33\%$ on HumanEval; and \textbf{(3) adversarially robust}, defending against agent adversarial attacks with merely $0. 3\%$ accuracy drop.

Details

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

AAAI Conference 2025 Conference Paper

Label-Free Backdoor Attacks in Vertical Federated Learning

  • Wei Shen
  • Wenke Huang
  • Guancheng Wan
  • Mang Ye

Vertical Federated Learning (VFL) involves multiple clients collaborating to train a global model, with distributed features of shared samples. While it becomes a critical privacy-preserving learning paradigm, its security can be significantly compromised by backdoor attacks, where a malicious client injects a target backdoor by manipulating local data. Existing attack methods in VFL rely on the assumption that the malicious client can obtain additional knowledge about task labels, which is not applicable in VFL. In this work, we investigate a new backdoor attack paradigm in VFL, Label-Free Backdoor Attacks (LFBA), which does not require any additional task label information and is feasible in VFL settings. Specifically, while existing methods assume access to task labels or target-class samples, we demonstrate that the gradients of local embeddings reflect the semantic information of labels. It can be utilized to construct the target poison sample set. Besides, we uncover that backdoor triggers tend to be ignored and under-fitted due to the learning of original features, which hinders backdoor task optimization. To address this, we propose selectively switching poison samples to disrupt feature learning, promoting backdoor task learning while maintaining accuracy on clean data. Extensive experiments demonstrate the effectiveness of our method in various settings.

PDF Details DOI

ICML Conference 2025 Conference Paper

Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning

  • Wenke Huang 0003
  • Jian Liang 0003
  • Zekun Shi
  • Didi Zhu
  • Guancheng Wan
  • He Li 0054
  • Bo Du 0001
  • Dacheng Tao

Multimodal Large Language Model (MLLM) has demonstrated strong generalization capabilities across diverse distributions and tasks, largely due to extensive pre-training datasets. Fine-tuning MLLM has become a common practice to improve performance on specific downstream tasks. However, during fine-tuning, MLLM often faces the risk of forgetting knowledge acquired during pre-training, which can result in a decline in generalization abilities. To balance the trade-off between generalization and specialization, we propose measuring the parameter importance for both pre-trained and fine-tuning distributions, based on frozen pre-trained weight magnitude and accumulated fine-tuning gradient values. We further apply an importance-aware weight allocation strategy, selectively updating relatively important parameters for downstream tasks. We conduct empirical evaluations on both image captioning and visual question-answering tasks using various MLLM architectures. The comprehensive experimental analysis demonstrates the effectiveness of the proposed solution, highlighting the efficiency of the crucial modules in enhancing downstream specialization performance while mitigating generalization degradation in MLLM Fine-Tuning.

Details

ICML Conference 2025 Conference Paper

Rethink GraphODE Generalization within Coupled Dynamical System

  • Guancheng Wan
  • Zijie Huang 0002
  • Wanjia Zhao
  • Xiao Luo 0001
  • Yizhou Sun
  • Wei Wang 0010

Coupled dynamical systems govern essential phenomena across physics, biology, and engineering, where components interact through complex dependencies. While Graph Ordinary Differential Equations (GraphODE) offer a powerful framework to model these systems, their generalization capabilities degrade severely under limited observational training data due to two fundamental flaws: (i) the entanglement of static attributes and dynamic states in the initialization process, and (ii) the reliance on context-specific coupling patterns during training, which hinders performance in unseen scenarios. In this paper, we propose a Generalizable GraphODE with disentanglement and regularization (GREAT) to address these challenges. Through systematic analysis via the Structural Causal Model, we identify backdoor paths that undermine generalization and design two key modules to mitigate their effects. The Dynamic-Static Equilibrium Decoupler (DyStaED) disentangles static and dynamic states via orthogonal subspace projections, ensuring robust initialization. Furthermore, the Causal Mediation for Coupled Dynamics (CMCD) employs variational inference to estimate latent causal factors, reducing spurious correlations and enhancing universal coupling dynamics. Extensive experiments across diverse dynamical systems demonstrate that ours outperforms state-of-the-art methods within both in-distribution and out-of-distribution.

Details

ICML Conference 2025 Conference Paper

S2FGL: Spatial Spectral Federated Graph Learning

  • Zihan Tan
  • Suyuan Huang 0003
  • Guancheng Wan
  • Wenke Huang 0003
  • He Li 0054
  • Mang Ye

Federated Graph Learning (FGL) combines the privacy-preserving capabilities of Federated Learning (FL) with the strong graph modeling capability of Graph Neural Networks (GNNs). Current research addresses subgraph-FL from the structural perspective, neglecting the propagation of graph signals on the spatial and spectral domains of the structure. From a spatial perspective, subgraph-FL introduces edge disconnections between clients, leading to disruptions in label signals and a degradation in the semantic knowledge of the global GNN. From a spectral perspective, spectral heterogeneity causes inconsistencies in signal frequencies across subgraphs, which makes local GNNs overfit the local signal propagation schemes. As a result, spectral client drift occurs, undermining global generalizability. To tackle the challenges, we propose a global knowledge repository to mitigate the challenge of poor semantic knowledge caused by label signal disruption. Furthermore, we design a frequency alignment to address spectral client drift. The combination of S patial and S pectral strategies forms our framework $S^2$FGL. Extensive experiments on multiple datasets demonstrate the superiority of $S^2$FGL. The code is available at https: //github. com/Wonder7racer/S2FGL. git.

Details

ICML Conference 2025 Conference Paper

Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models

  • Yangxu Liao
  • Wenke Huang 0003
  • Guancheng Wan
  • Jian Liang 0003
  • Bin Yang 0026
  • Mang Ye

Federated learning provides an efficient privacy-preserving distributed training framework for large language models, addressing the growing scarcity of publicly available training data while enabling the utilization of private datasets. While integrating large language model fine-tuning with federated learning emerges as a promising research direction, researchers pay limited attention to non-IID instruction-following scenarios. Our key insight is decomposing client updates into consensus and divergence components, enabling the model to maintain core capabilities while adapting to domain-specific knowledge. We propose a novel federated learning framework called FedICU (Splitting with I mportan C e-aware U pdating for Heterogeneous Fed erated Learning with Large Language Models), which introduces an aggregation mechanism that dynamically balances these components based on their contribution to global model performance, while implementing an importance-aware parameter updating strategy to prevent catastrophic forgetting and domain overfitting. Extensive experiments across diverse domains demonstrate that FedICU significantly outperforms existing federated learning approaches in terms of both generalization performance and domain adaptation. Our code is available at https: //github. com/liaosunny123/FedICU.

Details

AAAI Conference 2024 Conference Paper

Federated Graph Learning under Domain Shift with Generalizable Prototypes

  • Guancheng Wan
  • Wenke Huang
  • Mang Ye

Federated Graph Learning is a privacy-preserving collaborative approach for training a shared model on graph-structured data in the distributed environment. However, in real-world scenarios, the client graph data usually originate from diverse domains, this unavoidably hinders the generalization performance of the final global model. To address this challenge, we start the first attempt to investigate this scenario by learning a well-generalizable model. In order to improve the performance of the global model from different perspectives, we propose a novel framework called Federated Graph Learning with Generalizable Prototypes (FGGP). It decouples the global model into two levels and bridges them via prototypes. These prototypes, which are semantic centers derived from the feature extractor, can provide valuable classification information. At the classification model level, we innovatively eschew the traditional classifiers, then instead leverage clustered prototypes to capture fruitful domain information and enhance the discriminative capability of the classes, improving the performance of multi-domain predictions. Furthermore, at the feature extractor level, we go beyond traditional approaches by implicitly injecting distinct global knowledge and employing contrastive learning to obtain more powerful prototypes while enhancing the feature extractor generalization ability. Experimental results on various datasets are presented to validate the effectiveness of the proposed method.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference

  • Zihan Tan
  • Guancheng Wan
  • Wenke Huang
  • Mang Ye

Personalized Federated Graph Learning (pFGL) facilitates the decentralized training of Graph Neural Networks (GNNs) without compromising privacy while accommodating personalized requirements for non-IID participants. In cross-domain scenarios, structural heterogeneity poses significant challenges for pFGL. Nevertheless, previous pFGL methods incorrectly share non-generic knowledge globally and fail to tailor personalized solutions locally under domain structural shift. We innovatively reveal that the spectral nature of graphs can well reflect inherent domain structural shifts. Correspondingly, our method overcomes it by sharing generic spectral knowledge. Moreover, we indicate the biased message-passing schemes for graph structures and propose the personalized preference module. Combining both strategies, we propose our pFGL framework $\textbf{FedSSP}$ which $\textbf{S}$hares generic $\textbf{S}$pectral knowledge while satisfying graph $\textbf{P}$references. Furthermore, We perform extensive experiments on cross-dataset and cross-domain settings to demonstrate the superiority of our framework. The code is available at https: //github. com/OakleyTan/FedSSP.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning

  • Wenke Huang
  • Mang Ye
  • Zekun Shi
  • Guancheng Wan
  • He Li
  • Bo Du

Backdoor attacks pose a serious threat to federated systems, where malicious clients optimize on the triggered distribution to mislead the global model towards a predefined target. Existing backdoor defense methods typically require either homogeneous assumption, validation datasets, or client optimization conflicts. In our work, we observe that benign heterogeneous distributions and malicious triggered distributions exhibit distinct parameter importance degrees. We introduce the Fisher Discrepancy Cluster and Rescale (FDCR) method, which utilizes Fisher Information to calculate the degree of parameter importance for local distributions. This allows us to reweight client parameter updates and identify those with large discrepancies as backdoor attackers. Furthermore, we prioritize rescaling important parameters to expedite adaptation to the target distribution, encouraging significant elements to contribute more while diminishing the influence of trivial ones. This approach enables FDCR to handle backdoor attacks in heterogeneous federated learning environments. Empirical results on various heterogeneous federated scenarios under backdoor attacks demonstrate the effectiveness of our method.

PDF Details DOI

ICML Conference 2024 Conference Paper

S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning

  • Guancheng Wan
  • Yijun Tian 0001
  • Wenke Huang 0003
  • Nitesh V. Chawla
  • Mang Ye

Graph Contrastive Learning (GCL) has emerged as a highly effective self-supervised approach in graph representation learning. However, prevailing GCL methods confront two primary challenges: 1) They predominantly operate under homophily assumptions, focusing on low-frequency signals in node features while neglecting heterophilic edges that connect nodes with dissimilar features. 2) Their reliance on neighborhood aggregation for inference leads to scalability challenges and hinders deployment in real-time applications. In this paper, we introduce S3GCL, an innovative framework designed to tackle these challenges. Inspired by spectral GNNs, we initially demonstrate the correlation between frequency and homophily levels. Then, we propose a novel cosine-parameterized Chebyshev polynomial as low/high-pass filters to generate biased graph views. To resolve the inference dilemma, we incorporate an MLP encoder and enhance its awareness of graph context by introducing structurally and semantically neighboring nodes as positive pairs in the spatial domain. Finally, we formulate a cross-pass GCL objective between full-pass MLP and biased-pass GNN filtered features, eliminating the need for augmentation. Extensive experiments on real-world tasks validate S3GCL proficiency in generalization to diverse homophily levels and its superior inference efficiency.

Details

IJCAI Conference 2023 Conference Paper

Federated Graph Semantic and Structural Learning

  • Wenke Huang
  • Guancheng Wan
  • Mang Ye
  • Bo Du

Federated graph learning collaboratively learns a global graph neural network with distributed graphs, where the non-independent and identically distributed property is one of the major challenge. Most relative arts focus on traditional distributed tasks like images and voices, incapable of the graph structures. This paper firstly reveals that local client distortion is brought by both node-level semantics and graph-level structure. First, for node-level semantic, we find that contrasting nodes from distinct classes is beneficial to provide a well-performing discrimination. We pull the local node towards the global node of the same class and push them away from the global node of different classes. Second, we postulate that a well-structural graph neural network possesses similarity for neighbors due to the inherent adjacency relationships. However, aligning each node with adjacent nodes hinders discrimination due to the potential class inconsistency. We transform the adjacency relationships into the similarity distribution and leverage the global model to distill the relation knowledge into the local model, which preserves the structural information and discriminability of the local model. Empirical results on three graph datasets manifest the superiority of the proposed method over counterparts.

PDF Details DOI
v2026.09.13