動的グラフ世界モデリング：時間的文脈から未来のダイナミクスを学習する
Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context
動的グラフの未来状態を予測するため、ノードと関係の履歴・進化経路・将来表現を統合的に学習するDyG-WMフレームワークを提案し、リンク予測とノード分類で有効性を示した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Bo Li, Yue Yang, Yujin Huang, Siao Liu, David Lemphers, Sara E Rodriguez Gomez, Luke Borgnolo, Can Wang, Xin Zheng
分類: cs.LG
原文アブストラクト
Dynamic graph learning models how entities and their relations evolve from historical observations to predict future graph states. Existing methods do not fully address dynamic graph world modelling, which requires learning transitions from temporal context to future latent graph states. This is difficult for three reasons: nodes and relations rely on different historical evidence, structural evolution is path-dependent, and future snapshots provide sparse and realization-specific targets. We propose Dynamic Graph World Modelling (DyG-WM), the first framework to jointly predict future node and relation representations from temporal context by answering three questions: what has evolved, how it evolved, and what will evolve next. To capture what has evolved, a historical node-relation context encoder summarizes node-neighborhood trajectories and pair-specific histories. To characterize how it evolved, a node-relation path-signature encoder captures ordered structural changes. To predict what will evolve next, a dual-level joint-embedding objective predicts target-snapshot node and relation representations without reconstructing the raw graph. Experiments on 12 link-prediction and two node-classification datasets demonstrate the effectiveness of DyG-WM across both tasks.
