KG-BiLM: Knowledge Graph Embedding via Bidirectional Language Models
This work addresses the gap in knowledge representation learning for AI systems that require integrated structural and semantic reasoning, though it appears incremental as it builds on existing LM and KG methods.
The paper tackled the problem of unifying symbolic knowledge graphs with language models for richer semantic understanding by introducing KG-BiLM, a bidirectional LM framework that fuses structural and textual information, and it outperformed strong baselines in link prediction on standard benchmarks, especially on large-scale graphs with complex multi-hop relations.
Recent advances in knowledge representation learning (KRL) highlight the urgent necessity to unify symbolic knowledge graphs (KGs) with language models (LMs) for richer semantic understanding. However, existing approaches typically prioritize either graph structure or textual semantics, leaving a gap: a unified framework that simultaneously captures global KG connectivity, nuanced linguistic context, and discriminative reasoning semantics. To bridge this gap, we introduce KG-BiLM, a bidirectional LM framework that fuses structural cues from KGs with the semantic expressiveness of generative transformers. KG-BiLM incorporates three key components: (i) Bidirectional Knowledge Attention, which removes the causal mask to enable full interaction among all tokens and entities; (ii) Knowledge-Masked Prediction, which encourages the model to leverage both local semantic contexts and global graph connectivity; and (iii) Contrastive Graph Semantic Aggregation, which preserves KG structure via contrastive alignment of sampled sub-graph representations. Extensive experiments on standard benchmarks demonstrate that KG-BiLM outperforms strong baselines in link prediction, especially on large-scale graphs with complex multi-hop relations - validating its effectiveness in unifying structural information and textual semantics.