Lune

ACL Findings2026

Structure-Aware Zero-Shot Relational Learning for Knowledge Graphs without External Knowledge

Kuan Xu, Baoxin Zhang, Shuyue Fan, Ming Chen, Zhipeng Ke, Jian Yu, Xuezhong Zhou

Abstract

Zero-shot Relational Learning (ZRL) aims to perform knowledge graph completion when dealing with newly emerging relations that have no observed triples. However, existing ZRL methods typically rely on external knowledge (e.g., textual descriptions or curated annotations), which increases labeling costs and limits real-world applicability. To overcome this limitation, we propose a new Structure-Aware paradigm for ZRL, termed SAZRL, that performs ZRL without relying on external knowledge. SAZRL leverages intrinsic structural patterns in KGs to bridge semantic correlations for new relations with existing ones. It constructs structure-aware conditional query graphs based on shared entities and adaptive relation updating module to infer representations for new relations based on the query graphs. We conduct extensive experiments on three real-world benchmarks, NELL-ZS, Wiki-ZS and FB15K-ZS, demonstrating that SAZRL consistently surpasses state-of-the-art ZRL methods, achieving up to 10.66% improvement in MRR while eliminating external annotations.

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.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Towards Foundation Models for Knowledge Graph Reasoning cites InGram: Inductive Knowledge Graph Embedding via Relation Graphs
  • OntoZSL: Ontology-enhanced Zero-shot Learning cites Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs
  • InGram: Inductive Knowledge Graph Embedding via Relation Graphs cites How Attentive are Graph Attention Networks?
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on11

  1. How Attentive are Graph Attention Networks?Shaked Brody, Uri Alon, Eran YahavICLR 2022 · 1,717 citations
  2. OntoZSL: Ontology-enhanced Zero-shot LearningYuxia Geng, Jiaoyan Chen, Zhuo Chen, Jeff Z. Pan et al.WWW 2021 · 96 citations
  3. Towards Foundation Models for Knowledge Graph ReasoningMikhail Galkin, Xinyu Yuan, Hesham Mostafa, Jian Tang et al.ICLR 2024 · 95 citations
  4. Generative Adversarial Zero-Shot Relational Learning for Knowledge GraphsPengda Qin, Xin Wang, Wenhu Chen, Chunyun Zhang et al.AAAI 2020 · 93 citations
  5. InGram: Inductive Knowledge Graph Embedding via Relation GraphsJaejun Lee, Chanyoung Chung, Joyce Jiyoung WhangICML 2023 · 83 citations

Related papers

  1. Few-Shot Knowledge Graph CompletionChuxu Zhang, Huaxiu Yao, Chao Huang, Meng Jiang et al.AAAI 2020 · 238 citations
  2. Self-Supervised Knowledge Triplet Learning for Zero-Shot Question AnsweringPratyay Banerjee, Chitta BaralEMNLP 2020 · 20 citations
  3. Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph PropagationLikang Wu, Zhi Li, Hongke Zhao, Zhefeng Wang et al.KDD 2023 · 4 citations
  4. Few-shot Relational Reasoning via Connection Subgraph PretrainingQian Huang, Hongyu Ren, Jure LeskovecNeurIPS 2022 · 39 citations
  5. Generalized Relation Learning with Semantic Correlation Awareness for Link PredictionYao Zhang, Xu Zhang, Jun Wang, Hongru Liang et al.AAAI 2021 · 18 citations
Dusk over the sea between two cliffs drawn in fine vertical lines