4 papers
Temporal Heterogeneous Graph Pretraining for Relational Deep Learning
Yixin Peng, Er Jin, Diego Collarana +1
Relational deep learning models database rows and foreign-key links as a heterogeneous graph for prediction from record attributes and relational context. These graphs contain two…
VisKG-LM: Compiling Knowledge Graphs into Visual Memory for Multiple-Choice Question Answering
Yixin Peng, Er Jin, Shiwei Luo +2
Knowledge graphs are usually integrated into question answering by encoding a retrieved subgraph with a graph neural network and fusing it with the language model in the online inf…
TELLER: Dual-Path Iterative Preference Optimization for Table Entity Linking
Yixin Peng, Kehao Li, Stefan Decker
Entity linking in tables matches short and ambiguous cell mentions to their corresponding knowledge-base entities. Existing approaches typically rely on data preprocessing pipeline…
THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model
Yixin Peng, Diego Collarana, Er Jin +1
Temporal heterogeneous graphs offer a natural abstraction for dynamic relational systems in which diverse node and relation types co-exist and evolve over time. Learning on such gr…