paper-with-me

홈 › Papers

Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction

2023-05-22 · Adrian Kochsiek, Apoorv Saxena, Inderjeet Nair, Rainer Gemulla

We propose KGT5-context, a simple sequence-to-sequence model for link prediction (LP) in knowledge graphs (KG). Our work expands on KGT5, a recent LP model that exploits textual features of the KG, has small model size, and is scalable. To reach good predictive performance, however, KGT5 relies on an ensemble with a knowledge graph embedding model, which itself is excessively large and costly to use. In this short paper, we show empirically that adding contextual information - i.e., information about the direct neighborhood of the query entity - alleviates the need for a separate KGE model to obtain good performance. The resulting KGT5-context model is simple, reduces model size significantly, and obtains state-of-the-art performance in our experimental study.

📄 PDF Abstract BibTeX arXiv:2305.13059

Code (1)

uma-pi1/kgt5-context 공식 구현 pytorch

Tasks

Graph EmbeddingKnowledge Graph EmbeddingKnowledge GraphsLink PredictionPrediction

Similar Papers 제목 키워드 기반

CoKE: Contextualized Knowledge Graph Embedding

2019-11-06 · Quan Wang, Pingping Huang, Haifeng Wang, Songtai Dai 외

Knowledge graph embedding, which projects symbolic entities and relations into continuous vector spaces, is gaining increasing attention. Previous methods allow a single static embedding for each entity or relation, igno…

Graph EmbeddingKnowledge Graph EmbeddingLink PredictionRelation

Repeat-Aware Neighbor Sampling for Dynamic Graph Learning

2024-05-24 · Tao Zou, Yuhao Mao, Junchen Ye, Bowen Du

Dynamic graph learning equips the edges with time attributes and allows multiple links between two nodes, which is a crucial technology for understanding evolving data scenarios like traffic prediction and recommendation…

Graph LearningLink PredictionRecommendation SystemsTraffic Prediction

Label-Agnostic Sequence Labeling by Copying Nearest Neighbors

2019-06-10 · ACL 2019 7 · Sam Wiseman, Karl Stratos

Retrieve-and-edit based approaches to structured prediction, where structures associated with retrieved neighbors are edited to form new structures, have recently attracted increased interest. However, much recent work m…

FormStructured Prediction

k-Nearest Neighbors by Means of Sequence to Sequence Deep Neural Networks and Memory Networks

2018-04-27 · Yiming Xu, Diego Klabjan

k-Nearest Neighbors is one of the most fundamental but effective classification models. In this paper, we propose two families of models built on a sequence to sequence model and a memory network model to mimic the k-Nea…

General Classification

ProtAlign: Contrastive learning paradigm for Sequence and structure alignment

2026-03-06 · Aditya Ranganath, Hasin Us Sami, Kowshik Thopalli, Bhavya Kailkhura 외 arxiv

Protein language models often take into consideration the alignment between a protein sequence and its textual description. However, they do not take structural information into consideration. Traditional methods treat s…

Cross-Modal RetrievalContrastive Learning