{"type":"ScholarlyArticle","title":"LogicFusion: Differentiable Logical Rule Learning for Cancer Driver Gene Identification","authors":[{"name":"Bang Chen","slug":"bang-chen","given":"Bang","family":"Chen","affiliation":""},{"name":"Lijun Guo","slug":"lijun-guo","given":"Lijun","family":"Guo","affiliation":""},{"name":"Wentao He","slug":"wentao-he","given":"Wentao","family":"He","affiliation":""},{"name":"Guang Cao","slug":"guang-cao","given":"Guang","family":"Cao","affiliation":""},{"name":"Rong Zhang","slug":"rong-zhang","given":"Rong","family":"Zhang","affiliation":""}],"abstract":"Identifying cancer driver genes (CDGs) requires integrating heterogeneous biological networks, each encoding distinct mechanistic insights into tumorigenesis. Existing multi-network methods typically fuse views at the feature level or enforce uniform representations, which obscures network-specific signals and limits interpretability. To address this, we propose LogicFusion, a novel differentiable framework that treats each biological network as an independent probabilistic evidence source and explicitly learns how to combine them using logical reasoning. Specifically, LogicFusion maps the output of each view into probabilistic space as independent evidence, and learns a set of logical rules in a differentiable manner. These rules adaptively select and fuse these view evidences through logical conjunction (AND) and disjunction (OR). The final prediction is then obtained via gene-specific weighting. LogicFusion enables both high-accuracy CDG identification and interpretable attribution of predictions to specific networks. Experiments on pan-cancer and cancer-specific datasets show that LogicFusion consistently outperforms state-of-the-art methods, while providing transparency in multi-view genomic reasoning through learned logical rules.","doi":"10.24963/ijcai.2026/609","url":"https://ijcai.org/proceedings/2026/609","pdf":"https://ijcai.org/proceedings/2026/0609.pdf","markdown":"https://ijcai.org/proceedings/2026/609.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/609","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Multidisciplinary Topics and Applications","track":"Main Track","number":609,"pages":{"first":5468,"last":5476},"keywords":["Machine Learning: Multi-view learning","Multidisciplinary Topics and Applications: Bioinformatics","Machine Learning: Neuro-symbolic methods/Abductive Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}