A Good Neighbor, A Found Treasure: Mining Treasured Neighbors for Knowledge Graph Entity Typing

Jin, Zhuoran; Cao, Pengfei; Chen, Yubo; Kang, Ling; Zhao, Jianli

doi:10.18653/v1/2022.emnlp-main.31

Cited by 2 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, CET (Pan et al, 2021) introduces two mechanisms to fully utilize neighborhood information in an independent and aggregated manner. MiNer (Jin et al, 2022) proposes a neighborhood information aggregation module to aggregate both one-hop and multi-hop neighbors. However, these type of methods ignore other kind of semantic information, e.g., how types cluster together.…”

Section: Related Workmentioning

confidence: 99%

“…Indeed, sometimes only few neighbors are helpful for the prediction. We introduce a Multi-Head Attention mechanism Jin et al, 2022) with a Mixture-of-Experts (MHAM) to distinguish the information of each head. We compute the final score as:…”

Section: Entity Typing Predictionmentioning

confidence: 99%

“…We jointly train the multi-view contrastive learning and entity type prediction tasks to obtain an end-to-end model. For entity type prediction, we adopt the false-negative aware (FNA) loss function (Pan et al, 2021;Jin et al, 2022), denoted L ET . We further combine the multi-view contrastive learning loss with the FNA loss, so we can obtain the joint loss function:…”

Section: Entity Typing Predictionmentioning

confidence: 99%

“…We compare MCLET with three types of baselines. (i) embedding-based models: ETE (Moon et al, 2017), ConnectE (Zhao et al,Datasets FB15kET YAGO43kET Metrics MRR Hits@1 Hits@3 Hits@10 MRR Hits@1 Hits@3 Hits@10 Embedding-based methods ETE (Moon et al, 2020) and CORE (Ge et al, 2021); (ii) GNNbased models: HMGCN (Jin et al, 2019), At-tEt (Zhuo et al, 2022), ConnectE-MRGAT , RACE2T (Zou et al, 2022a), CompGCN (Vashishth et al, 2020) RGCN (Pan et al, 2021), CET (Pan et al, 2021), and MiNer (Jin et al, 2022); (iii) transformer-based models: CoKE (Wang et al, 2019), HittER (Chen et al, 2021) and TET (Hu et al, 2022a).…”

Section: Entity Typing Predictionmentioning

confidence: 99%

“…A wide variety of approaches to KGET have been already proposed, including embedding- (Moon et al, 2017;Zhao et al, 2020), transformer- (Wang et al, 2019;Hu et al, 2022a) and graph neural network (GNNs) based methods (Pan et al, 2021;Jin et al, 2022). Each of these approaches have their own disadvantages: embedding-based methods ignore the existing neighbor information, transformer-based are computationally costly due to the use of multiple transformers to encode different neighbors and GNNs-based ignore important higher-level semantic content beyond what is readily available in the graph-structure.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Multi-view Contrastive Learning for Entity Typing over Knowledge Graphs

Hu,

Basulto,

Xiang

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Knowledge graph entity typing (KGET) aims at inferring plausible types of entities in knowledge graphs. Existing approaches to KGET focus on how to better encode the knowledge provided by the neighbors and types of an entity into its representation. However, they ignore the semantic knowledge provided by the way in which types can be clustered together. In this paper, we propose a novel method called Multi-view Contrastive Learning for knowledge graph Entity Typing (MCLET), which effectively encodes the coarse-grained knowledge provided by clusters into entity and type embeddings. MCLET is composed of three modules: i) Multi-view Generation and Encoder module, which encodes structured information from entity-type, entity-cluster and cluster-type views; ii) Cross-view Contrastive Learning module, which encourages different views to collaboratively improve view-specific representations of entities and types; iii) Entity Typing Prediction module, which integrates multi-head attention and a Mixture-of-Experts strategy to infer missing entity types. Extensive experiments show the strong performance of MCLET compared to the state-of-the-art.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Entity Typing Predictionmentioning

confidence: 99%

Section: Entity Typing Predictionmentioning

confidence: 99%