# Learning to Denoise Biomedical Knowledge Graph for Robust Molecular Interaction Prediction

arXiv: https://arxiv.org/abs/2312.06682 · HTML: https://mlsanity.com/paper/2312.06682/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 55 references that are in the map.
- First posted on arXiv 9 Dec 2023.

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

- [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)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Inductive Relation Prediction by Subgraph Reasoning](https://mlsanity.com/paper/1911.06962/) (2019)
- [Modeling polypharmacy side effects with graph convolutional networks](https://mlsanity.com/paper/1802.00543/) (2018)
- [GNNGuard: Defending Graph Neural Networks against Adversarial Attacks](https://mlsanity.com/paper/2006.08149/) (2020)
- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [Knowledge Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2205.00976/) (2022)
- [Improving Question Answering by Commonsense-Based Pre-Training](https://mlsanity.com/paper/1809.03568/) (2018)
- [GSLB: The Graph Structure Learning Benchmark](https://mlsanity.com/paper/2310.05174/) (2023)
- [Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure](https://mlsanity.com/paper/2211.10738/) (2022)
- [SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarization](https://mlsanity.com/paper/2010.01450/) (2020)
- [AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning](https://mlsanity.com/paper/2205.15319/) (2022)
- [Subgraph Neighboring Relations Infomax for Inductive Link Prediction on Knowledge Graphs](https://mlsanity.com/paper/2208.00850/) (2022)
- [Self-Guided Learning to Denoise for Robust Recommendation](https://mlsanity.com/paper/2204.06832/) (2022)
- [Graph Collaborative Signals Denoising and Augmentation for Recommendation](https://mlsanity.com/paper/2304.03344/) (2023)
- [Robust Preference-Guided Denoising for Graph based Social Recommendation](https://mlsanity.com/paper/2303.08346/) (2023)
- [Comprehensive evaluation of deep and graph learning on drug-drug interactions prediction](https://mlsanity.com/paper/2306.05257/) (2023)
- [Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks](https://mlsanity.com/paper/2010.08516/) (2020)
- [Trustworthy Knowledge Graph Completion Based on Multi-sourced Noisy Data](https://mlsanity.com/paper/2201.08580/) (2022)
- [Heterogeneous Relational Reasoning in Knowledge Graphs with Reinforcement Learning](https://mlsanity.com/paper/2003.06050/) (2020)

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

- [Rethinking Regularization Methods for Knowledge Graph Completion](https://mlsanity.com/paper/2505.23442/) (2025)
- [Y-Mol: A Multiscale Biomedical Knowledge-Guided Large Language Model for Drug Development](https://mlsanity.com/paper/2410.11550/) (2024)
- [RareAgent: Self-Evolving Reasoning for Drug Repurposing in Rare Diseases](https://mlsanity.com/paper/2510.05764/) (2025)
- [MolBridge: Atom-Level Joint Graph Refinement for Robust Drug-Drug Interaction Event Prediction](https://mlsanity.com/paper/2510.20448/) (2025)
- [Retrieval-Augmented Multimodal Learning for Enzyme-Substrate Interaction Prediction Under Low-Homology Shift](https://mlsanity.com/paper/2606.22823/) (2026)

## Abstract (arXiv)

Molecular interaction prediction plays a crucial role in forecasting unknown interactions between molecules, such as drug-target interaction (DTI) and drug-drug interaction (DDI), which are essential in the field of drug discovery and therapeutics. Although previous prediction methods have yielded promising results by leveraging the rich semantics and topological structure of biomedical knowledge graphs (KGs), they have primarily focused on enhancing predictive performance without addressing the presence of inevitable noise and inconsistent semantics. This limitation has hindered the advancement of KG-based prediction methods. To address this limitation, we propose BioKDN (Biomedical Knowledge Graph Denoising Network) for robust molecular interaction prediction. BioKDN refines the reliable structure of local subgraphs by denoising noisy links in a learnable manner, providing a general module for extracting task-relevant interactions. To enhance the reliability of the refined structure, BioKDN maintains consistent and robust semantics by smoothing relations around the target interaction. By maximizing the mutual information between reliable structure and smoothed relations, BioKDN emphasizes informative semantics to enable precise predictions. Experimental results on real-world datasets show that BioKDN surpasses state-of-the-art models in DTI and DDI prediction tasks, confirming the effectiveness and robustness of BioKDN in denoising unreliable interactions within contaminated KGs