mlsanityData to 14 Oct 2026

Explainable Biomedical Recommendations via Reinforcement Learning Reasoning on Knowledge Graphs

arXiv 2111.10625 ↗First posted 20 Nov 2021cs.LG cs.AI cs.SIcited by 7

Not on the map. Why?

Abstract (arXiv)

For Artificial Intelligence to have a greater impact in biology and medicine, it is crucial that recommendations are both accurate and transparent. In other domains, a neurosymbolic approach of multi-hop reasoning on knowledge graphs has been shown to produce transparent explanations. However, there is a lack of research applying it to complex biomedical datasets and problems. In this paper, the approach is explored for drug discovery to draw solid conclusions on its applicability. For the first time, we systematically apply it to multiple biomedical datasets and recommendation tasks with fair benchmark comparisons. The approach is found to outperform the best baselines by 21.7% on average whilst producing novel, biologically relevant explanations.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 31 of its 70 references that are in the map. First posted on arXiv 20 Nov 2021.

Builds on

31 of 70 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  4. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  5. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  6. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  7. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  8. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  9. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
  10. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 932
  11. 2017Convolutional 2D Knowledge Graph Embeddingscited by 730
  12. 2017DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoningcited by 266
19 more
  1. 2021Reinforcement learning based recommender systems: A surveycited by 188
  2. 2017End-to-End Differentiable Provingcited by 161
  3. 2017Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learningcited by 161
  4. 2020Combining Deep Reinforcement Learning and Search for Imperfect-Information Gamescited by 114
  5. 2018Multi-Hop Knowledge Graph Reasoning with Reward Shapingcited by 102
  6. 2019Reinforcement Knowledge Graph Reasoning for Explainable Recommendationcited by 102
  7. 2019Learning to Exploit Long-term Relational Dependencies in Knowledge Graphscited by 83
  8. 2019A Re-evaluation of Knowledge Graph Completion Methodscited by 73
  9. 2019Probabilistic Logic Neural Networks for Reasoningcited by 69
  10. 2020DGL-KE: Training Knowledge Graph Embeddings at Scalecited by 67
  11. 2020Network Medicine Framework for Identifying Drug Repurposing Opportunities for COVID-19cited by 39
  12. 2021A Review of Biomedical Datasets Relating to Drug Discovery: A Knowledge Graph Perspectivecited by 38
  13. 2018M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Searchcited by 34
  14. 2019OpenBioLink: A benchmarking framework for large-scale biomedical link predictioncited by 28
  15. 2021Neural Multi-Hop Reasoning With Logical Rules on Biomedical Knowledge Graphscited by 25
  16. 2020Reasoning on Knowledge Graphs with Debate Dynamicscited by 16
  17. 2020On the Ambiguity of Rank-Based Evaluation of Entity Alignment or Link Prediction Methodscited by 13
  18. 2021Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretabilitycited by 10
  19. 2020Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoningcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 1; 2024: 1; 2025: 2.

7 papers.

  1. 2025Biomedical Knowledge Graph: A Survey of Domains, Tasks, and Real-World Applicationscited by 6
  2. 2025A Study on Neuro-Symbolic Artificial Intelligence: Healthcare Perspectivescited by 5
  3. 2022Efficient multi-relational network representation using primescited by 1
  4. 2023Analysing Biomedical Knowledge Graphs using Prime Adjacency Matricescited by 1
  5. 2022Learning to Discover Medicinescited by 0
  6. 2022TigerLily: Finding drug interactions in silico with the Graphcited by 0
  7. 2024From Primes to Paths: Enabling Fast Multi-Relational Graph Analysiscited by 0