Deep Reinforcement Learning for Entity Alignment
Embedding-based methods have attracted increasing attention in recent entity alignment (EA) studies. Although great promise they can offer, there are still several limitations. The most notable is that they identify the aligned entities based on cosine similarity, ignoring the semantics underlying the embeddings themselves. Furthermore, these methods are shortsighted, heuristically selecting the closest entity as the target and allowing multiple entities to match the same candidate. To address these limitations, we model entity alignment as a sequential decision-making task, in which an agent sequentially decides whether two entities are matched or mismatched based on their representation vectors. The proposed reinforcement learning (RL)-based entity alignment framework can be flexibly adapted to most embedding-based EA methods. Our experiments demonstrate that it consistently advances the performance of several state-of-the-art methods, with a maximum improvement of 31.1% on Hits@1.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingDeep Reinforcement LearningEntity Alignmentreinforcement-learningReinforcement LearningReinforcement Learning (RL)Sequential Decision MakingSimilar Papers 제목 키워드 기반
Deep Reinforcement Learning for Entity Alignment
Embedding-based methods have attracted increasing attention in recent entity alignment (EA) studies. Although great promise they can offer, there are still several limitations. The most notable is that they identify the …
Decision MakingDeep Reinforcement LearningEntity Alignmentreinforcement-learning+3Reinforcement Learning based Collective Entity Alignment with Adaptive Features
Entity alignment (EA) is the task of identifying the entities that refer to the same real-world object but are located in different knowledge graphs (KGs). For entities to be aligned, existing EA solutions treat them sep…
Decision MakingEntity AlignmentKnowledge Graphsreinforcement-learning+2Resolving the Identity Crisis in Text-to-Image Generation
State-of-the-art text-to-image models suffer from a persistent identity crisis when generating scenes with multiple humans: producing duplicate faces, merging identities, and miscounting individuals. We present DisCo (Re…
Text-to-Image GenerationReinforcement LearningConflict-Aware Pseudo Labeling via Optimal Transport for Entity Alignment
Entity alignment aims to discover unique equivalent entity pairs with the same meaning across different knowledge graphs (KGs). Existing models have focused on projecting KGs into a latent embedding space so that inheren…
Entity AlignmentEntity EmbeddingsKnowledge GraphsPseudo LabelCombating Confirmation Bias: A Unified Pseudo-Labeling Framework for Entity Alignment
Entity alignment (EA) aims at identifying equivalent entity pairs across different knowledge graphs (KGs) that refer to the same real-world identity. To circumvent the shortage of seed alignments provided for training, r…
Entity AlignmentKnowledge GraphsPseudo Label