Two Facets of the Same Optimization Coin: Model Degradation and Representation Collapse in Graph Foundation Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Xunkai, Su, Daohan, Liu, Sicheng, Zhang, Ru, Li, Zhenjun, Zhou, Bing, Li, Rong-Hua, Wang, Guoren
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Toward Effective Multimodal Graph Foundation Model: A Divide-and-Conquer Based Approach
di: Liu, Sicheng, et al.
Pubblicazione: (2026)

DiRW: Path-Aware Digraph Learning for Heterophily
di: Su, Daohan, et al.
Pubblicazione: (2024)

Toward General and Robust LLM-enhanced Text-attributed Graph Learning
di: Zhang, Zihao, et al.
Pubblicazione: (2025)

Toward General Digraph Contrastive Learning: A Dual Spatial Perspective
di: Su, Daohan, et al.
Pubblicazione: (2025)

Towards Data-centric Machine Learning on Directed Graphs: a Survey
di: Sun, Henan, et al.
Pubblicazione: (2024)

When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach
di: Zhang, Zhihan, et al.
Pubblicazione: (2025)

State Space Models over Directed Graphs
di: She, Junzhi, et al.
Pubblicazione: (2025)

Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGs
di: Fan, Bowen, et al.
Pubblicazione: (2025)

Rethinking Node-wise Propagation for Large-scale Graph Learning
di: Li, Xunkai, et al.
Pubblicazione: (2024)

Toward Effective Digraph Representation Learning: A Magnetic Adaptive Propagation based Approach
di: Li, Xunkai, et al.
Pubblicazione: (2025)

LightDiC: A Simple yet Effective Approach for Large-scale Digraph Representation Learning
di: Li, Xunkai, et al.
Pubblicazione: (2024)

DOGMA: Weaving Structural Information into Data-centric Single-cell Transcriptomics Analysis
di: Zhang, Ru, et al.
Pubblicazione: (2026)

Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification
di: Sun, Henan, et al.
Pubblicazione: (2023)

Knowledge-Driven Federated Graph Learning on Model Heterogeneity
di: Wu, Zhengyu, et al.
Pubblicazione: (2025)

HIAL: A New Paradigm for Hypergraph Active Learning via Influence Maximization
di: Hou, Yanheng, et al.
Pubblicazione: (2025)

FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modeling
di: Wu, Zhengyu, et al.
Pubblicazione: (2025)

Towards Unbiased Federated Graph Learning: Label and Topology Perspectives
di: Wu, Zhengyu, et al.
Pubblicazione: (2025)

MagicDock: Toward Docking-oriented De Novo Ligand Design via Gradient Inversion
di: Chen, Zekai, et al.
Pubblicazione: (2025)

Rethinking Client-oriented Federated Graph Learning
di: Chen, Zekai, et al.
Pubblicazione: (2025)

ScaDyG:A New Paradigm for Large-scale Dynamic Graph Learning
di: Wu, Xiang, et al.
Pubblicazione: (2025)

GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective
di: Wang, Xu, et al.
Pubblicazione: (2026)

GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments
di: Du, Enjun, et al.
Pubblicazione: (2025)

Federated Prototype Graph Learning
di: Wu, Zhengyu, et al.
Pubblicazione: (2025)

Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms
di: Wu, Xiang, et al.
Pubblicazione: (2026)

STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning
di: Chen, Zekai, et al.
Pubblicazione: (2026)

OpenGU: A Comprehensive Benchmark for Graph Unlearning
di: Fan, Bowen, et al.
Pubblicazione: (2025)

Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks
di: Li, Xunkai, et al.
Pubblicazione: (2024)

Toward Scalable Graph Unlearning: A Node Influence Maximization based Approach
di: Li, Xunkai, et al.
Pubblicazione: (2025)

Towards Effective and General Graph Unlearning via Mutual Evolution
di: Li, Xunkai, et al.
Pubblicazione: (2024)

FedGTA: Topology-aware Averaging for Federated Graph Learning
di: Li, Xunkai, et al.
Pubblicazione: (2024)

TFPS: A Temporal Filtration-enhanced Positive Sample Set Construction Method for Implicit Collaborative Filtering
di: Wu, Jiayi, et al.
Pubblicazione: (2026)

Unlocking Graph Structure Learning with Tree-Guided Large Language Models
di: Zhang, Zhihan, et al.
Pubblicazione: (2025)

CAMPA: Efficient and Aligned Multimodal Graph Learning via Decoupled Propagation and Aggregation
di: Su, Daohan, et al.
Pubblicazione: (2026)

Federated Graph Unlearning
di: Ai, Yuming, et al.
Pubblicazione: (2025)

RoleMAG: Learning Neighbor Roles in Multimodal Graphs
di: Zuo, Yilong, et al.
Pubblicazione: (2026)

DANCE: Dynamic, Available, Neighbor-gated Condensation for Federated Text-Attributed Graphs
di: Chen, Zekai, et al.
Pubblicazione: (2026)

LION: A Clifford Neural Paradigm for Multimodal-Attributed Graph Learning
di: Li, Xunkai, et al.
Pubblicazione: (2026)

Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity
di: Zhang, Sirui, et al.
Pubblicazione: (2026)

Toward Data-centric Directed Graph Learning: An Entropy-driven Approach
di: Li, Xunkai, et al.
Pubblicazione: (2025)

BoostFGL: Boosting Fairness in Federated Graph Learning
di: Chen, Zekai, et al.
Pubblicazione: (2026)