# TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph

arXiv: https://arxiv.org/abs/2104.07302 · HTML: https://mlsanity.com/paper/2104.07302/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 15 Apr 2021.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [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)
- [Large-scale Simple Question Answering with Memory Networks](https://mlsanity.com/paper/1506.02075/) (2015)
- [Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision](https://mlsanity.com/paper/1611.00020/) (2016)
- [Retrospective Reader for Machine Reading Comprehension](https://mlsanity.com/paper/2001.09694/) (2020)
- [Hierarchical Graph Network for Multi-hop Question Answering](https://mlsanity.com/paper/1911.03631/) (2019)
- [Cognitive Graph for Multi-Hop Reading Comprehension at Scale](https://mlsanity.com/paper/1905.05460/) (2019)
- [Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents](https://mlsanity.com/paper/1911.00484/) (2019)
- [An Interpretable Reasoning Network for Multi-Relation Question Answering](https://mlsanity.com/paper/1801.04726/) (2018)
- [Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base](https://mlsanity.com/paper/2002.06115/) (2020)
- [SimpleQuestions Nearly Solved: A New Upperbound and Baseline Approach](https://mlsanity.com/paper/1804.08798/) (2018)
- [Simple Question Answering with Subgraph Ranking and Joint-Scoring](https://mlsanity.com/paper/1904.04049/) (2019)

## Built on by (most cited first, 30 of 60)

- [Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning](https://mlsanity.com/paper/2310.01061/) (2023)
- [GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning](https://mlsanity.com/paper/2405.20139/) (2024)
- [UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph](https://mlsanity.com/paper/2212.00959/) (2022)
- [RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering](https://mlsanity.com/paper/2109.08678/) (2021)
- [Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering](https://mlsanity.com/paper/2210.01613/) (2022)
- [TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Bases](https://mlsanity.com/paper/2210.12925/) (2022)
- [Complex Knowledge Base Question Answering: A Survey](https://mlsanity.com/paper/2108.06688/) (2021)
- [KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases](https://mlsanity.com/paper/2308.11761/) (2023)
- [ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models](https://mlsanity.com/paper/2310.08975/) (2023)
- [Program Transfer for Answering Complex Questions over Knowledge Bases](https://mlsanity.com/paper/2110.05743/) (2021)
- [ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph](https://mlsanity.com/paper/2401.00158/) (2023)
- [KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph](https://mlsanity.com/paper/2312.15880/) (2023)
- [ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2210.13650/) (2022)
- [Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement](https://mlsanity.com/paper/2402.00745/) (2024)
- [Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs](https://mlsanity.com/paper/2210.10375/) (2022)
- [Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection](https://mlsanity.com/paper/2109.05808/) (2021)
- [Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering](https://mlsanity.com/paper/2305.15056/) (2023)
- [BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering](https://mlsanity.com/paper/2507.04127/) (2025)
- [Semantic Structure based Query Graph Prediction for Question Answering over Knowledge Graph](https://mlsanity.com/paper/2204.10194/) (2022)
- [Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs](https://mlsanity.com/paper/2506.10508/) (2025)
- [FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs](https://mlsanity.com/paper/2501.09957/) (2025)
- [KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding](https://mlsanity.com/paper/2307.03115/) (2023)
- [NuTrea: Neural Tree Search for Context-guided Multi-hop KGQA](https://mlsanity.com/paper/2310.15484/) (2023)
- [EPERM: An Evidence Path Enhanced Reasoning Model for Knowledge Graph Question and Answering](https://mlsanity.com/paper/2502.16171/) (2025)
- [Improving Question Answering over Knowledge Graphs Using Graph Summarization](https://mlsanity.com/paper/2203.13570/) (2022)
- [CBR-iKB: A Case-Based Reasoning Approach for Question Answering over Incomplete Knowledge Bases](https://mlsanity.com/paper/2204.08554/) (2022)
- [SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.15272/) (2024)
- [DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTS](https://mlsanity.com/paper/2508.00719/) (2025)
- [QAGCN: Answering Multi-Relation Questions via Single-Step Implicit Reasoning over Knowledge Graphs](https://mlsanity.com/paper/2206.01818/) (2022)
- [How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering](https://mlsanity.com/paper/2401.05777/) (2024)

## Abstract (arXiv)

Multi-hop Question Answering (QA) is a challenging task because it requires precise reasoning with entity relations at every step towards the answer. The relations can be represented in terms of labels in knowledge graph (e.g., textitspouse) or text in text corpus (e.g., textitthey have been married for 26 years). Existing models usually infer the answer by predicting the sequential relation path or aggregating the hidden graph features. The former is hard to optimize, and the latter lacks interpretability. In this paper, we propose TransferNet, an effective and transparent model for multi-hop QA, which supports both label and text relations in a unified framework. TransferNet jumps across entities at multiple steps. At each step, it attends to different parts of the question, computes activated scores for relations, and then transfer the previous entity scores along activated relations in a differentiable way. We carry out extensive experiments on three datasets and demonstrate that TransferNet surpasses the state-of-the-art models by a large margin. In particular, on MetaQA, it achieves 100% accuracy in 2-hop and 3-hop questions. By qualitative analysis, we show that TransferNet has transparent and interpretable intermediate results.