Lune

ACL Findings2026

AnyGraph: Graph Foundation Model in the Wild

Lianghao Xia, Chao Huang

Abstract

The ubiquity of text-attributed graph data has highlighted the need for graph learning models with exceptional generalization across diverse textual and structural contexts.Current approaches struggle to extract generalizable insights from heterogeneous graph data, requiring extensive fine-tuning and limiting versatility across domains.In this work, we propose AnyGraph, a unified graph foundation model designed to handle key challenges: i) Structure Heterogenity -addressing distribution shift in graph structural patterns; ii) Feature Heterogenity -handling diverse textual representations; iii) Fast Adaptation -efficiently adapting to new graph-text domains.We build AnyGraph upon a Graph Mixture-of-Experts (MoE) architecture with a lightweight expert routing mechanism that effectively manages cross-domain distribution shift.Extensive experiments on 38 diverse datasets demonstrate AnyGraph's strong zeroshot performance across domains with significant distribution shift, validating its fast adaptation ability and scaling law emergence.Our model is open-sourced and available

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

10 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Bridging Input Feature Spaces Towards Graph Foundation Models cites Towards A Universal Graph Structural Encoder
  • Towards A Universal Graph Structural Encoder cites Graph Contrastive Learning with Augmentations
  • Self-supervised Graph Learning for Recommendation cites LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
  • Self-supervised Graph Learning for Recommendation cites Graph Contrastive Learning with Augmentations
  • Self-supervised Graph Learning for Recommendation cites Graph Contrastive Learning with Adaptive Augmentation
  • Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement cites RiemannGFM: Learning a Graph Foundation Model from Riemannian Geometry
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers10

  1. RiemannGFM: Learning a Graph Foundation Model from Riemannian GeometryLi Sun, Zhenhao Huang, Suyang Zhou, Qiqi Wan et al.WWW 2025 · 31 citations
  2. Towards Effective Federated Graph Foundation Model via Mitigating Knowledge EntanglementYinlin Zhu, Xunkai Li, Jishuo Jia, Miao Hu et al.NeurIPS 2025 · 17 citations
  3. GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and PreservationZihao Guo, Qingyun Sun, Ziwei Zhang, Haonan Yuan et al.NeurIPS 2025 · 10 citations
  4. Towards A Universal Graph Structural EncoderJialin Chen, Haolan Zuo, Haoyu Wang, Siqi Miao et al.WWW 2026 · 6 citations
  5. Bridging Input Feature Spaces Towards Graph Foundation ModelsMoshe Eliasof, Krishna Sri Ipsit Mantri, Beatrice Bevilacqua, Bruno Ribeiro et al.ICLR 2026 · 4 citations

Builds on29

  1. LightGCN: Simplifying and Powering Graph Convolution Network for RecommendationXiangnan He, Kuan Deng, Xiang Wang, Yan Li et al.SIGIR 2020 · 4,448 citations
  2. Graph Contrastive Learning with AugmentationsYuning You, Tianlong Chen, Yongduo Sui, Ting Chen et al.NeurIPS 2020 · 3,042 citations
  3. How Attentive are Graph Attention Networks?Shaked Brody, Uri Alon, Eran YahavICLR 2022 · 1,717 citations
  4. Self-supervised Graph Learning for RecommendationJiancan Wu, Xiang Wang, Fuli Feng, Xiangnan He et al.SIGIR 2021 · 1,476 citations
  5. Graph Contrastive Learning with Adaptive AugmentationYanqiao Zhu, Yichen Xu, Feng Yu, Qiang Liu et al.WWW 2021 · 1,415 citations

Related papers

  1. Out-of-Distribution Graph Models MergingYidi Wang, Ziyue Qiao, Jiawei Gu, Xubin Zheng et al.ICLR 2026
  2. UniGraph2: Learning a Unified Embedding Space to Bind Multimodal GraphsYufei He, Yuan Sui, Xiaoxin He, Yue Liu et al.WWW 2025 · 37 citations
  3. OpenGraph: Towards Open Graph Foundation ModelsLianghao Xia, Ben Kao, Chao HuangEMNLP Findings 2024 · 18 citations
  4. UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed GraphsYufei He, Yuan Sui, Xiaoxin He, Bryan HooiKDD 2025 · 8 citations
  5. How Much Can Transfer? BRIDGE: Bounded Multi-Domain Graph Foundation Model with Generalization GuaranteesHaonan Yuan, Qingyun Sun, Junhua Shi, Xingcheng Fu et al.ICML 2025
Dusk over the sea between two cliffs drawn in fine vertical lines