5 papers · 1 filter
AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs
Yubo Wang, Haoyang Li, Fei Teng +1
Graph-based retrieval-augmented generation (Graph-based RAG) has demonstrated significant potential in enhancing Large Language Models (LLMs) with structured knowledge. However, ex…
Understanding the Embedding Models on Hyper-relational Knowledge Graph
Yubo Wang, Shimin Di, Zhili Wang +4
Recently, Hyper-relational Knowledge Graphs (HKGs) have been proposed as an extension of traditional Knowledge Graphs (KGs) to better represent real-world facts with additional qua…
A Selective Learning Method for Temporal Graph Continual Learning
Hanmo Liu, Shimin Di, Haoyang Li +3
Node classification is a key task in temporal graph learning (TGL). Real-life temporal graphs often introduce new node classes over time, but existing TGL methods assume a fixed se…
Cardinality Estimation on Hyper-relational Knowledge Graphs
Fei Teng, Haoyang Li, Shimin Di +1
Cardinality Estimation (CE) for query is to estimate the number of results without execution, which is an effective index in query optimization. Recently, CE for queries over knowl…
UniCL: A Universal Contrastive Learning Framework for Large Time Series Models
Jiawei Li, Jingshu Peng, Haoyang Li +1
Time-series analysis plays a pivotal role across a range of critical applications, from finance to healthcare, which involves various tasks, such as forecasting and classification.…