# SQUIRE: A Sequence-to-sequence Framework for Multi-hop Knowledge Graph Reasoning

arXiv: https://arxiv.org/abs/2201.06206 · HTML: https://mlsanity.com/paper/2201.06206/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 17 Jan 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [Offline Reinforcement Learning as One Big Sequence Modeling Problem](https://mlsanity.com/paper/2106.02039/) (2021)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [TuckER: Tensor Factorization for Knowledge Graph Completion](https://mlsanity.com/paper/1901.09590/) (2019)
- [DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning](https://mlsanity.com/paper/1707.06690/) (2017)
- [DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs](https://mlsanity.com/paper/1911.00055/) (2019)
- [End-to-End Differentiable Proving](https://mlsanity.com/paper/1705.11040/) (2017)
- [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)
- [Bridging the Gap between Training and Inference for Neural Machine Translation](https://mlsanity.com/paper/1906.02448/) (2019)
- [Multi-Hop Knowledge Graph Reasoning with Reward Shaping](https://mlsanity.com/paper/1808.10568/) (2018)
- [Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones](https://mlsanity.com/paper/2110.14923/) (2021)
- [Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations](https://mlsanity.com/paper/1908.11513/) (2019)
- [Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph](https://mlsanity.com/paper/2010.01899/) (2020)
- [Reinforced Anytime Bottom Up Rule Learning for Knowledge Graph Completion](https://mlsanity.com/paper/2004.04412/) (2020)
- [Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability](https://mlsanity.com/paper/2104.06751/) (2021)
- [Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning](https://mlsanity.com/paper/2005.00571/) (2020)
- [KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion](https://mlsanity.com/paper/2004.13631/) (2020)

## Built on by (most cited first, 6 of 6)

- [Generative Knowledge Graph Construction: A Review](https://mlsanity.com/paper/2210.12714/) (2022)
- [Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimization](https://mlsanity.com/paper/2212.09567/) (2022)
- [Look Globally and Reason: Two-stage Path Reasoning over Sparse Knowledge Graphs](https://mlsanity.com/paper/2407.18556/) (2024)
- [IMKGA-SM: Interpretable Multimodal Knowledge Graph Answer Prediction via Sequence Modeling](https://mlsanity.com/paper/2301.02445/) (2023)
- [Theseus in the Graph: Towards Traceable Multi-Hop Graph Navigation](https://mlsanity.com/paper/2609.14528/) (2026)
- [Relations Are Channels: Knowledge Graph Embedding via Kraus Decompositions](https://mlsanity.com/paper/2605.10317/) (2026)

## Abstract (arXiv)

Multi-hop knowledge graph (KG) reasoning has been widely studied in recent years to provide interpretable predictions on missing links with evidential paths. Most previous works use reinforcement learning (RL) based methods that learn to navigate the path towards the target entity. However, these methods suffer from slow and poor convergence, and they may fail to infer a certain path when there is a missing edge along the path. Here we present SQUIRE, the first Sequence-to-sequence based multi-hop reasoning framework, which utilizes an encoder-decoder Transformer structure to translate the query to a path. Our framework brings about two benefits: (1) It can learn and predict in an end-to-end fashion, which gives better and faster convergence; (2) Our Transformer model does not rely on existing edges to generate the path, and has the flexibility to complete missing edges along the path, especially in sparse KGs. Experiments on standard and sparse KGs show that our approach yields significant improvement over prior methods, while converging 4x-7x faster.