{"type":"ScholarlyArticle","title":"MolHFCNet: Enhancing Molecular Graph Representations with Hierarchical Feature Combining and Hybrid Pretraining","authors":[{"name":"Duy-Long Nguyen","slug":"duy-long-nguyen","given":"Duy-Long","family":"Nguyen","affiliation":""},{"name":"Duc-Luong Ho-Viet","slug":"duc-luong-ho-viet","given":"Duc-Luong","family":"Ho-Viet","affiliation":""},{"name":"Anh-Thu Ngo-Tran","slug":"anh-thu-ngo-tran","given":"Anh-Thu","family":"Ngo-Tran","affiliation":""},{"name":"Quang H. Nguyen","slug":"quang-h-nguyen","given":"Quang H.","family":"Nguyen","affiliation":""},{"name":"Binh P. Nguyen","slug":"binh-p-nguyen","given":"Binh P.","family":"Nguyen","affiliation":""}],"abstract":"Efficient molecular property prediction is crucial in bioinformatics and cheminformatics, with applications in drug discovery, materials science, and chemical engineering. This paper introduces MolHFCNet, a graph neural network designed to enhance molecular representation learning. At its core, the n-Hierarchical Features Combining (n-HFC) module aggregates information across multiple hierarchical feature spaces, effectively capturing both local and global graph structures. Unlike conventional models, n-HFC maintains computational complexity comparable to a single full-dimensional graph layer while supporting either 2D or 3D molecular graphs, ensuring flexibility across tasks. Furthermore, we propose a novel graph pretraining strategy that integrates predictive and contrastive learning, enabling the model to capture local chemical interactions and global molecular contexts for robust embeddings. Experimental results on benchmark datasets demonstrate MolHFCNet’s superior accuracy and efficiency compared to state-of-the-art methods, highlighting the potential of high-order hierarchical feature learning for advancing molecular graph analysis. Our code is available at https://github.com/ndlongvn/MolHFCNet.","doi":"10.24963/ijcai.2025/1035","url":"https://ijcai.org/proceedings/2025/1035","pdf":"https://ijcai.org/proceedings/2025/1035.pdf","markdown":"https://ijcai.org/proceedings/2025/1035.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/1035","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"AI4Tech: AI Enabling Technologies","track":"AI4Tech: AI Enabling Technologies","number":1035,"pages":{"first":9313,"last":9321},"keywords":["Advanced AI4Tech: Deep AI4Tech","Domain-specific AI4Tech: AI4Medicine and AI4Drug","Domain-specific AI4Tech: AI4Biotech"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}