{"type":"ScholarlyArticle","title":"Distribution-Aware Energy Minimization: Physical-Inspired Efficient Active Learning and Quantum Potentials","authors":[{"name":"Zhicheng Yao","slug":"zhicheng-yao","given":"Zhicheng","family":"Yao","affiliation":""},{"name":"Wenguo Yang","slug":"wenguo-yang","given":"Wenguo","family":"Yang","affiliation":""},{"name":"Yancheng Chen","slug":"yancheng-chen","given":"Yancheng","family":"Chen","affiliation":""},{"name":"Dun Ma","slug":"dun-ma","given":"Dun","family":"Ma","affiliation":""},{"name":"Shengminjie Chen","slug":"shengminjie-chen","given":"Shengminjie","family":"Chen","affiliation":""},{"name":"Xiaoming Sun","slug":"xiaoming-sun","given":"Xiaoming","family":"Sun","affiliation":""}],"abstract":"Active learning aims to maximize model performance with minimal annotation costs by selecting the most informative samples from large unlabeled pools, which often face a budget dilemma: uncertainty-based methods induce redundancy under low budgets, while representativeness-based methods struggle to mine challenging samples under high budgets. Although some heuristic parameter interpolation schemes attempt to bridge this gap, such strategies suffer from a misalignment between theoretical assumptions and real-world distributions, failing to achieve a good exploration-exploitation balance across all scenarios. In this paper, we propose a general active learning framework based on Distribution-Aware Energy Minimization, which reformulates sample selection as minimizing the energy function for the distributional discrepancy between the selected subset and the global uncertainty field. This physical-inspired perspective naturally derives a Hamiltonian comprising attractive terms and repulsive terms, mathematically achieving an intrinsic and dynamic balance between uncertainty and representativeness. Furthermore, we transform the optimization objective to the ground-state search of an Ising Model, enabling efficient solutions via Coherent Ising Machine. Extensive numerical experiments show that our method outperforms prior state-of-the-art methods across multi-budget regimes on several benchmark datasets. Validation on a real quantum hardware also demonstrates the potential for quantum computer in future large-scale selection tasks.","doi":"10.24963/ijcai.2026/225","url":"https://ijcai.org/proceedings/2026/225","pdf":"https://ijcai.org/proceedings/2026/0225.pdf","markdown":"https://ijcai.org/proceedings/2026/225.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/225","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":"Computer Vision","track":"Main Track","number":225,"pages":{"first":2019,"last":2027},"keywords":["Computer Vision: Efficiency and Optimization","Machine Learning: Supervised Learning","Machine Learning: Active learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}