基於實體-屬性二象性的異質圖建模

Abstract

異質資訊網路（Heterogeneous Information Networks, HINs）提供了一個具有表現力的框架，能夠整合不同類型的實體與關係，通常定義於一個固定的綱要（schema）之下。然而，現有研究多倚賴預設的綱要結構，忽略了資料在不同建模選擇下呈現的差異，進而對下游任務造成潛在影響。 本研究提出「實體與屬性二象性（entity–attribute duality）」的概念：屬性可以被原子化為具關聯的實體，而實體亦可作為其他實體的屬性。此原則啟發我們設計出 atomic HIN 的範式，旨在系統性地規範結構建模選擇，並提升異質圖模型的表達能力。 在此基礎上，我們進一步提出一個任務導向的綱要最佳化（schema refinement）框架，能將既有資料集視為某一特定設計選擇下的產物，並系統性地探索更適合下游任務的綱要結構。實驗結果顯示，在結合 schema refinement 後，僅使用一個簡化版的關係圖卷積網（simplified Relational GCN, sRGCN），即可於八個涵蓋節點層級與邊層級任務的資料集上達到當前最佳（state-of-the-art）表現；進一步使用先進的異質圖神經網路（HGNNs）則可進一步提升效果。這表明，異質圖的結構建模選擇對於學習表現具有關鍵性影響。 最後，我們公開 atomic HINs 的最佳化結構與完整框架，為建立更具原則性的模型評分奠定基礎，並為未來在綱要感知式學習（schema-aware learning）、自動結構探索（automated structure discovery）以及下一代 HGNNs 的研究提供新方向。

Heterogeneous Information Networks (HINs) provide a powerful framework for modeling multi-typed entities and relations, typically defined under a fixed schema. Yet, most research assumes this structure is given, overlooking the fact that alternative designs can emphasize different aspects of the data and substantially influence downstream performance. As a theoretical foundation for such designs, we introduce the principle of entity-attribute duality: attributes can be atomized as entities with their associated relations, while entities can, in turn, serve as attributes of others. This principle motivates atomic HIN, a canonical representation that makes all modeling choices explicit and achieves maximal expressiveness. Building on this foundation, we propose a systematic framework for task-specific schema refinement. Within this framework, we demonstrate that widely used benchmarks correspond to heuristic refinements of the atomic HIN—often far from optimal. Across eight datasets, refinement alone enables a simplified Relational GCN (sRGCN) to reach state-of-the-art performance on node- and link-level tasks, with further gains from advanced HGNNs. These results highlight schema design as a key dimension in heterogeneous graph modeling. By releasing the atomic HINs, searched schemas, and refinement framework, we enable principled benchmarking and open the way for future work on schema-aware learning, automated structure discovery, and next-generation HGNNs.