# QAGCN: Answering Multi-Relation Questions via Single-Step Implicit Reasoning over Knowledge Graphs

arXiv: https://arxiv.org/abs/2206.01818 · HTML: https://mlsanity.com/paper/2206.01818/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 3 Jun 2022.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [Key-Value Memory Networks for Directly Reading Documents](https://mlsanity.com/paper/1606.03126/) (2016)
- [PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text](https://mlsanity.com/paper/1904.09537/) (2019)
- [Variational Reasoning for Question Answering with Knowledge Graph](https://mlsanity.com/paper/1709.04071/) (2017)
- [Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text](https://mlsanity.com/paper/1809.00782/) (2018)
- [Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning](https://mlsanity.com/paper/1711.05851/) (2017)
- [Large-scale Simple Question Answering with Memory Networks](https://mlsanity.com/paper/1506.02075/) (2015)
- [Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals](https://mlsanity.com/paper/2101.03737/) (2021)
- [Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering](https://mlsanity.com/paper/2202.13296/) (2022)
- [TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph](https://mlsanity.com/paper/2104.07302/) (2021)
- [Question Answering with Subgraph Embeddings](https://mlsanity.com/paper/1406.3676/) (2014)
- [An Interpretable Reasoning Network for Multi-Relation Question Answering](https://mlsanity.com/paper/1801.04726/) (2018)
- [Lambda Dependency-Based Compositional Semantics](https://mlsanity.com/paper/1309.4408/) (2013)
- [CBR-iKB: A Case-Based Reasoning Approach for Question Answering over Incomplete Knowledge Bases](https://mlsanity.com/paper/2204.08554/) (2022)

## Built on by (most cited first, 5 of 5)

- [Lexicalization Is All You Need: Examining the Impact of Lexical Knowledge in a Compositional QALD System](https://mlsanity.com/paper/2411.03906/) (2024)
- [Knowledge Fusion via Bidirectional Information Aggregation](https://mlsanity.com/paper/2507.08704/) (2025)
- [GNN2R: Weakly-Supervised Rationale-Providing Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2312.02317/) (2023)
- [Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey](https://mlsanity.com/paper/2607.09666/) (2026)
- [The Graph Language: How Knowledge Graphs Speak to Large Language Models](https://mlsanity.com/paper/2608.01175/) (2026)

## Abstract (arXiv)

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