Lune

ICDE2021Top-tier venue

Efficient Relation-aware Scoring Function Search for Knowledge Graph Embedding

Shimin Di, Quanming Yao, Yongqi Zhang, Lei Chen

Abstract

The scoring function, which measures the plausibility of triplets in knowledge graphs (KGs), is the key to ensure the excellent performance of KG embedding, and its design is also an important problem in the literature. Automated machine learning (AutoML) techniques have recently been introduced into KG to design task-aware scoring functions, which achieve the state-of-the-art performance in KG embedding. However, the effectiveness of searched scoring functions is still not as good as desired. In this paper, observing that existing scoring functions can exhibit distinct performance on different semantic patterns, we are motivated to explore such semantics by searching relationa-ware scoring functions. But the relation-aware search requires a much larger search space than the previous one. Hence, we propose to encode the space as a supernet and propose an efficient alternative minimization algorithm to search through the supernet in a one-shot manner. Finally, experimental results on benchmark datasets demonstrate that the proposed method can efficiently search relation-aware scoring functions, and achieve better embedding performance than state-of-the-art methods1.

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

  • A Message Passing Neural Network Space for Better Capturing Data-dependent Receptive Fields cites AutoGEL: An Automated Graph Neural Network with Explicit Link Information
  • A Message Passing Neural Network Space for Better Capturing Data-dependent Receptive Fields cites Revisiting Injective Attacks on Recommender Systems
  • Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding cites Efficient Neural Architecture Search via Proximal Iterations
  • Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding cites AutoSF: Searching Scoring Functions for Knowledge Graph Embedding
  • MMKGR: Multi-hop Multi-modal Knowledge Graph Reasoning cites AutoSF: Searching Scoring Functions for Knowledge Graph Embedding
  • AutoGEL: An Automated Graph Neural Network with Explicit Link Information cites Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding
  • AutoGEL: An Automated Graph Neural Network with Explicit Link Information cites Efficient Neural Architecture Search via Proximal Iterations
  • AutoGEL: An Automated Graph Neural Network with Explicit Link Information cites AutoSF: Searching Scoring Functions for Knowledge Graph Embedding
  • Revisiting Injective Attacks on Recommender Systems cites AutoGEL: An Automated Graph Neural Network with Explicit Link Information
  • AutoSF: Searching Scoring Functions for Knowledge Graph Embedding cites Efficient Neural Architecture Search via Proximal Iterations
  • Customized Subgraph Selection and Encoding for Drug-drug Interaction Prediction cites Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding
  • Customized Subgraph Selection and Encoding for Drug-drug Interaction Prediction cites AutoGEL: An Automated Graph Neural Network with Explicit Link Information
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers10

  1. AutoGEL: An Automated Graph Neural Network with Explicit Link InformationZhili Wang, Shimin Di, Lei ChenNeurIPS 2021 · 46 citations
  2. MMKGR: Multi-hop Multi-modal Knowledge Graph ReasoningShangfei Zheng, Weiqing Wang, Jianfeng Qu, Hongzhi Yin et al.ICDE 2023 · 40 citations
  3. Revisiting Injective Attacks on Recommender SystemsHaoyang Li, Shimin Di, Lei ChenNeurIPS 2022 · 26 citations
  4. Customized Subgraph Selection and Encoding for Drug-drug Interaction PredictionHaotong Du, Quanming Yao, Juzheng Zhang, Yang Liu et al.NeurIPS 2024 · 23 citations
  5. A Message Passing Neural Network Space for Better Capturing Data-dependent Receptive FieldsZhili Wang, Shimin Di, Lei ChenKDD 2023 · 8 citations

Builds on3

  1. Efficient Neural Architecture Search via Proximal IterationsQuanming Yao, Ju Xu, Wei-Wei Tu, Zhanxing ZhuAAAI 2020 · 108 citations
  2. AutoSF: Searching Scoring Functions for Knowledge Graph EmbeddingYongqi Zhang, Quanming Yao, Wenyuan Dai, Lei ChenICDE 2020 · 89 citations
  3. Interstellar: Searching Recurrent Architecture for Knowledge Graph EmbeddingYongqi Zhang, Quanming Yao, Lei ChenNeurIPS 2020 · 25 citations

Related papers

  1. Message Function Search for Knowledge Graph EmbeddingShimin Di, Lei ChenWWW 2023 · 10 citations
  2. ReliK: A Reliability Measure for Knowledge Graph EmbeddingsMaximilian K. Egger, Wenyue Ma, Davide Mottin, Panagiotis Karras et al.WWW 2024 · 2 citations
  3. ReInceptionE: Relation-Aware Inception Network with Joint Local-Global Structural Information for Knowledge Graph EmbeddingZhiwen Xie, Guangyou Zhou, Jin Liu, Jimmy Xiangji HuangACL 2020 · 64 citations
  4. SEEK: Segmented Embedding of Knowledge GraphsWentao Xu, Shun Zheng, Liang He, Bin Shao et al.ACL 2020 · 31 citations
  5. Efficient Hyper-parameter Search for Knowledge Graph EmbeddingYongqi Zhang, Zhanke Zhou, Quanming Yao, Yong LiACL 2022 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines