Research map / Graph learning / Knowledge and temporal graphs
Towards Synergistic Path-based Explanations for Knowledge Graph Completion: Exploration and Evaluation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Explores and evaluates synergistic path-based explanations for knowledge graph completion models, addressing how sets of paths jointly explain predictions.
Problem
Explaining knowledge graph completion predictions by identifying which KG patterns (paths) are most determinant to a KGE model's prediction; existing path-based explanations treat paths individually and may miss their joint effect.
Approach
Moves from individual path explanations toward synergistic (jointly considered) path-based explanations for KGC, and proposes an evaluation of such explanations. Details beyond the abstract are not available.
Closest papers by meaning
- KGCRR: An Effective Metric-Driven Knowledge Graph Completion Framework by Designing a Novel Upper Bound Function with Adaptive Approximation to Reciprocal Rank (AAAI 2025 · similarity 0.89)
- Modeling Knowledge Graphs with Composite Reasoning (AAAI 2024 · similarity 0.89)
- Replacing Paths with Connection-Biased Attention for Knowledge Graph Completion (AAAI 2025 · similarity 0.88)
- Anchoring Path for Inductive Relation Prediction in Knowledge Graphs (AAAI 2024 · similarity 0.87)
- KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge (NeurIPS 2024 · similarity 0.87)
- Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.