English

CHAINSFORMER: Numerical Reasoning on Knowledge Graphs from a Chain Perspective

Artificial Intelligence 2025-04-22 v1 Machine Learning

Abstract

Reasoning over Knowledge Graphs (KGs) plays a pivotal role in knowledge graph completion or question answering systems, providing richer and more accurate triples and attributes. As numerical attributes become increasingly essential in characterizing entities and relations in KGs, the ability to reason over these attributes has gained significant importance. Existing graph-based methods such as Graph Neural Networks (GNNs) and Knowledge Graph Embeddings (KGEs), primarily focus on aggregating homogeneous local neighbors and implicitly embedding diverse triples. However, these approaches often fail to fully leverage the potential of logical paths within the graph, limiting their effectiveness in exploiting the reasoning process. To address these limitations, we propose ChainsFormer, a novel chain-based framework designed to support numerical reasoning. Chainsformer not only explicitly constructs logical chains but also expands the reasoning depth to multiple hops. Specially, we introduces Relation-Attribute Chains (RA-Chains), a specialized logic chain, to model sequential reasoning patterns. ChainsFormer captures the step-by-step nature of multi-hop reasoning along RA-Chains by employing sequential in-context learning. To mitigate the impact of noisy chains, we propose a hyperbolic affinity scoring mechanism that selects relevant logic chains in a variable-resolution space. Furthermore, ChainsFormer incorporates an attention-based numerical reasoner to identify critical reasoning paths, enhancing both reasoning accuracy and transparency. Experimental results demonstrate that ChainsFormer significantly outperforms state-of-the-art methods, achieving up to a 20.0% improvement in performance. The implementations are available at https://github.com/zhaodazhuang2333/ChainsFormer.

Keywords

Cite

@article{arxiv.2504.14282,
  title  = {CHAINSFORMER: Numerical Reasoning on Knowledge Graphs from a Chain Perspective},
  author = {Ze Zhao and Bin Lu and Xiaoying Gan and Gu Tang and Luoyi Fu and Xinbing Wang},
  journal= {arXiv preprint arXiv:2504.14282},
  year   = {2025}
}

Comments

Accepted to ICDE 2025

R2 v1 2026-06-28T23:04:14.218Z