Scholar
Siwei Liu
Google Scholar ID: 8gO4UDIAAAAJ
Lecturer (Assistant Professor) at University of Aberdeen
Citations & Impact
Citations
415
H-index
10
i10-index
10
Publications
20
Co-authors
19
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'EvoAgentX: An automated framework for evolving agentic workflows' accepted as a Demo Paper by EMNLP 2025
- Paper 'RRGMambaFormer: A hybrid Transformer-Mamba architecture for radiology report generation' accepted by Expert Systems with Applications
- Paper 'Active Learning for Multi-Class Drug-Drug Interactions Prediction' accepted by IEEE International Conference on Bioinformatics and Biomedicine
- Paper 'PASCL: supervised contrastive learning with perturbative augmentation for particle decay reconstruction' accepted by Machine Learning: Science and Technology
- Paper 'Enhancing Graph Neural Networks via Memorized Global Information' accepted by ACM Transactions on the Web
- Paper 'Heterogeneous biomedical entity representation learning for gene–disease association prediction' accepted by Briefings in Bioinformatics
- Paper 'BPP: A Platform for Automatic Biochemical Pathway Prediction' accepted by Briefings in Bioinformatics
- Paper 'A Social-aware Gaussian Pre-trained Model for Effective Cold-start Recommendation' accepted by Information Processing and Management
- Paper 'Messages Are Never Propagated Alone: Collaborative Hypergraph Neural Network for Time-series Forecasting' accepted by TPAMI
- Paper 'Sequence pre-training-based graph neural network for predicting lncRNA-miRNA associations' accepted by Briefings in Bioinformatics (IF=9.5)
- Paper 'HMCDA: a novel method based on the heterogeneous graph neural network and metapath for circRNA-disease associations prediction' accepted by BMC Bioinformatics (IF=3.327)
- Paper 'Leveraging Relational Graph Neural Network for Transductive Model Ensemble' accepted by SIGKDD (CCF A)
- Paper 'Graph neural pre-training for recommendation with side information' accepted by ACM TOIS (CCF A)
- Paper 'An MLP-based Algorithm for Efficient Contrastive Graph Recommendations' accepted by ACM SIGIR (CCF A)
- Co-founder and main contributor of the open-source project Beta-Recsys for Building, Evaluating and Tuning Automated Recommender Systems
- Launched the open-source project EvoAgentX
- Gave a talk on Graph Neural Networks at UN Big Data Hackathon 2022 in November 2022
