QAGCN: Answering Multi-Relation Questions via Single-Step Implicit Reasoning over Knowledge Graphs
This addresses the problem of complex and inefficient reasoning mechanisms in multi-relation QA for researchers and practitioners, offering a simpler and more adoptable solution, though it is incremental as it builds on existing GCN approaches.
The paper tackles multi-relation question answering over knowledge graphs by proposing QAGCN, a method using single-step implicit reasoning via a question-aware GCN, which achieved competitive or superior performance compared to state-of-the-art explicit-reasoning methods.
Multi-relation question answering (QA) is a challenging task, where given questions usually require long reasoning chains in KGs that consist of multiple relations. Recently, methods with explicit multi-step reasoning over KGs have been prominently used in this task and have demonstrated promising performance. Examples include methods that perform stepwise label propagation through KG triples and methods that navigate over KG triples based on reinforcement learning. A main weakness of these methods is that their reasoning mechanisms are usually complex and difficult to implement or train. In this paper, we argue that multi-relation QA can be achieved via end-to-end single-step implicit reasoning, which is simpler, more efficient, and easier to adopt. We propose QAGCN -- a Question-Aware Graph Convolutional Network (GCN)-based method that includes a novel GCN architecture with controlled question-dependent message propagation for the implicit reasoning. Extensive experiments have been conducted, where QAGCN achieved competitive and even superior performance compared to state-of-the-art explicit-reasoning methods. Our code and pre-trained models are available in the repository: https://github.com/ruijie-wang-uzh/QAGCN