Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases
Not on the map. Why?
Abstract (arXiv)
We investigate the entity alignment (EA) problem with unlabeled dangling cases, meaning that partial entities have no counterparts in the other knowledge graph (KG), and this type of entity remains unlabeled. To address this challenge, we propose the framework textitLambda for dangling detection and then entity alignment. Lambda features a GNN-based encoder called KEESA with spectral contrastive learning for EA and a positive-unlabeled learning algorithm for dangling detection called iPULE. iPULE offers theoretical guarantees of unbiasedness, uniform deviation bounds, and convergence. Experimental results demonstrate that each component contributes to overall performances that are superior to baselines, even when baselines additionally exploit 30% of dangling entities labeled for training.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 32 of its 43 references that are in the map. First posted on arXiv 16 Mar 2024.
Builds on
32 of 43 references.
References · 32
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
- 2017Word Translation Without Parallel Datacited by 487
- 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 403
- 2017Positive-Unlabeled Learning with Non-Negative Risk Estimatorcited by 219
- 2016Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignmentcited by 128
- 2017Cross-lingual Entity Alignment via Joint Attribute-Preserving Embeddingcited by 127
- 2020A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphscited by 120
- 2019Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregationcited by 101
- 2019Multi-Channel Graph Neural Network for Entity Alignmentcited by 86
- 2019Learning to Exploit Long-term Relational Dependencies in Knowledge Graphscited by 83
20 more
- 2019Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Networkcited by 68
- 2020Relational Reflection Entity Alignmentcited by 53
- 2016Optimality of the Johnson-Lindenstrauss Lemmacited by 42
- 2016Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learningcited by 41
- 2020TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphscited by 41
- 2021Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Miningcited by 37
- 2023Learning nonparametric latent causal graphs with unknown interventionscited by 34
- 2022SelfKG: Self-Supervised Entity Alignment in Knowledge Graphscited by 32
- 2023Contrastive Learning Is Spectral Clustering On Similarity Graphcited by 25
- 2021Knowing the No-match: Entity Alignment with Dangling Casescited by 20
- 2022ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similaritiescited by 20
- 2023Unsupervised Entity Alignment for Temporal Knowledge Graphscited by 19
- 2023Vision, Deduction and Alignment: An Empirical Study on Multi-modal Knowledge Graph Alignmentcited by 19
- 2022LightEA: A Scalable, Robust, and Interpretable Entity Alignment Framework via Three-view Label Propagationcited by 18
- 2020An Industry Evaluation of Embedding-based Entity Alignmentcited by 15
- 2021Graph Entropy Guided Node Embedding Dimension Selection for Graph Neural Networkscited by 13
- 2022A Probabilistic Graph Coupling View of Dimension Reductioncited by 13
- 2022An Accurate Unsupervised Method for Joint Entity Alignment and Dangling Entity Detectioncited by 7
- 2022Dangling-Aware Entity Alignment with Mixed High-Order Proximitiescited by 4
- 2022Semi-constraint Optimal Transport for Entity Alignment with Dangling Casescited by 2
Built on by
Citing papers per year: 2025: 1; 2026: 2.
3 papers.