Harnessing Structural Context for Entity Alignment Foundation Models

• URL: http://arxiv.org/abs/2606.06109v1
• Date: Thu, 04 Jun 2026 12:57:36 GMT
• Title: Harnessing Structural Context for Entity Alignment Foundation Models
• Abstract summary: We introduce ContextEA, an enhanced encoder-decoder framework for transferable EA.<n>On the encoder side, we introduce a cross-KG interaction encoder that unifies the two KGs with anchor bridges and performs earlier relation-aware cross-graph propagation.<n>On the decoder side, we introduce a structural calibration decoder that calibrates alignment scores with entity-level, neighborhood-level, relation-level, and anchor-aware structural evidence.
• Score: 47.50117201618907
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Entity alignment (EA) aims to identify equivalent entities across heterogeneous knowledge graphs (KGs) and is a key component of knowledge fusion and cross-KG reasoning. The recent EA foundation model demonstrates that alignment knowledge, once pretrained, can be directly applied to diverse previously unseen KG pairs. However, it still underuses structural context in two places: cross-KG interaction is weak during encoding, and final candidate ranking still relies too heavily on coarse similarity. We address these limitations with ContextEA, an enhanced encoder-decoder framework for transferable EA. On the encoder side, we introduce a cross-KG interaction encoder that unifies the two KGs with anchor bridges and performs earlier relation-aware cross-graph propagation. On the decoder side, we introduce a structural calibration decoder that calibrates alignment scores with entity-level, neighborhood-level, relation-level, and anchor-aware structural evidence. This design strengthens both structural context construction and structural context exploitation while remaining lightweight. Experiments on 29 EA datasets in OpenEA, SRPRS, and DBP show consistent gains over strong transferable baselines. Notably, the pretrained ContextEA already surpasses the finetuned baselines on all three benchmark groups, demonstrating substantially stronger transfer to unseen KGs. These results suggest that explicitly harnessing structural context is an effective direction for improving EA foundation models.

Related papers

• COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models [52.024920838442576]
  We present the first unified multimodal framework that grounds composition-intent control in a single system spanning both composition perception and composition-guided generation.<n>We construct Comp-11, a large-scale dataset with an 11-class taxonomy and reasoning-augmented annotations.
  arXiv  Detail & Related papers  (2026-06-27T02:43:13Z)
• BA-T: An Iterative Transformer for Two-View Bundle Adjustment [53.16990349592508]
  We propose BA-T, an iterative Transformer that implements BA-style structured updates as a repeatable layer in implicit token space.<n> experiments demonstrate that BA-T progressively improves pose and reconstruction accuracy across iterations.<n>BA-T provides a compact, efficient, and structural alternative to depth-heavy attention, enabling accurate 3D reconstruction within a lightweight architecture.
  arXiv  Detail & Related papers  (2026-06-02T07:51:14Z)
• KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning [51.44698654440413]
  Knowledge graph (KG) foundation models aim to generalize across graphs with unseen entities and relations by learning transferable relational structure.<n>We propose KGPFN, a KG foundation model that unifies transferable relational regularities with inference-time in-context learning.<n>Experiments on 57 KG benchmarks demonstrate that KGPFN achieves strong adaptation to previously unseen graphs through in-context learning alone.
  arXiv  Detail & Related papers  (2026-05-14T14:41:19Z)
• Breaking the Reasoning Horizon in Entity Alignment Foundation Models [22.785226234096882]
  Existing EA models lack transferability and are incapable of aligning unseen KGs without retraining.<n>We propose a EA foundation model driven by a parallel encoding strategy.<n>We utilize seed EA pairs as local anchors to guide the information flow, initializing and encoding two parallel streams simultaneously.
  arXiv  Detail & Related papers  (2026-01-29T02:18:45Z)
• AlphaFold Database Debiasing for Robust Inverse Folding [58.792020809180336]
  We introduce a Debiasing Structure AutoEncoder (DeSAE) that learns to reconstruct native-like conformations from intentionally corrupted backbone geometries.<n>At inference, applying DeSAE to AFDB structures produces debiased structures that significantly improve inverse folding performance.
  arXiv  Detail & Related papers  (2025-06-10T02:25:31Z)
• DERA: Dense Entity Retrieval for Entity Alignment in Knowledge Graphs [3.500936203815729]
  We propose a dense entity retrieval framework for Entity Alignment (EA) We leverage language models to uniformly encode various features of entities and facilitate nearest entity search across Knowledge Graphs (KGs) Our approach achieves state-of-the-art performance compared to existing EA methods.
  arXiv  Detail & Related papers  (2024-08-02T10:12:42Z)
• A Fused Gromov-Wasserstein Framework for Unsupervised Knowledge Graph Entity Alignment [22.526341223786375]
  In this paper, we introduce FGWEA, an unsupervised entity alignment framework that leverages the Fused Gromov-Wasserstein (FGW) distance. We show that FGWEA surpasses 21 competitive baselines, including cutting-edge supervised entity alignment methods.
  arXiv  Detail & Related papers  (2023-05-11T05:17:54Z)
• Entity Alignment with Reliable Path Reasoning and Relation-Aware Heterogeneous Graph Transformer [5.960613525368867]
  We propose a more effective entity alignment framework, RPR-RHGT, which integrates relation and path structure information. An initial reliable path reasoning algorithm is developed to generate the paths favorable for EA task from the relation structures of Knowledge Graphs. To efficiently capture heterogeneous features in entity neighborhoods, a relation-aware heterogeneous graph transformer is designed.
  arXiv  Detail & Related papers  (2022-05-18T09:12:37Z)
• Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment [100.19568734815732]
  Entity alignment (EA) aims at building a unified Knowledge Graph (KG) of rich content by linking the equivalent entities from various KGs. attribute triples can also provide crucial alignment signal but have not been well explored yet. We propose to utilize an attributed value encoder and partition the KG into subgraphs to model the various types of attribute triples efficiently.
  arXiv  Detail & Related papers  (2020-10-07T08:03:58Z)
• Inductive Learning on Commonsense Knowledge Graph Completion [89.72388313527296]
  Commonsense knowledge graph (CKG) is a special type of knowledge graph (CKG) where entities are composed of free-form text. We propose to study the inductive learning setting for CKG completion where unseen entities may present at test time. InductivE significantly outperforms state-of-the-art baselines in both standard and inductive settings on ATOMIC and ConceptNet benchmarks.
  arXiv  Detail & Related papers  (2020-09-19T16:10:26Z)
• Degree-Aware Alignment for Entities in Tail [11.153455121529236]
  We propose a novel framework for entity alignment (EA) We identify entity's degree as important guidance to effectively fuse two different sources of information. For post-alignment, we propose to complement original KGs with facts from their counterparts by using confident EA results as anchors.
  arXiv  Detail & Related papers  (2020-05-25T14:15:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.