Partial multi-label learning and complementary multi-label learning are two popular weakly supervised multi-label classification paradigms that aim to alleviate the high annotation costs of collecting precisely annotated multi-label data. In partial multi-label learning, each instance is annotated with a candidate label set, among which only some labels are relevant; in complementary multi-label learning, each instance is annotated with complementary labels indicating the classes to which the instance does not belong. Existing consistent approaches for the two paradigms either require accurate estimation of the generation process of candidate or complementary labels or assume a uniform distribution to eliminate the estimation problem. However, both conditions are usually difficult to satisfy in real-world scenarios. In this paper, we propose consistent approaches that do not rely on the aforementioned conditions to handle both problems in a unified way. Specifically, we propose two risk estimators based on first- and second-order strategies. Theoretically, we prove consistency w.r.t. two widely used multi-label classification evaluation metrics and derive convergence rates for the estimation errors of the proposed risk estimators. Empirically, extensive experimental results on both real-world and synthetic datasets validate the effectiveness of our proposed approaches against state-of-the-art methods.
From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing
School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）；National Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）；Hong Kong University of Science and Technology（香港科学与技术大学）；Frontier Robotics（前沿机器人）
Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark
Shanghai University of Finance and Economics（上海金融学院）；Ant Group（蚂蚁集团）；Key Laboratory of Interdisciplinary Research of Computation and Economics（计算与经济交叉学科重点实验室）
VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training
College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）；Honor Device Co., Ltd（荣耀设备有限公司）；Institute of Trustworthy Embodied AI, Fudan University（复旦大学可信具身人工智能研究院）；Shanghai Key Laboratory of Multimodal Embodied AI（上海多模态具身人工智能重点实验室）
How to Train Text Summarization Model with Weak Supervisions
School of Computer Science and Technology, North University of China（中北大学计算机科学与技术学院）；School of Semiconductor and Physics, North University of China（中北大学半导体与物理学院）
Rethinking the Unsupervised Paradigm in Time Series Anomaly Detection: An Empirical Study and Minimalist Baseline
School of Future Technology, South China University of Technology（华南理工大学未来技术学院）；Pengcheng Laboratory（鹏城实验室）；School of Computer Science and Engineering, South China University of Technology（华南理工大学计算机科学与工程学院）
MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation
Shanghai Jiao Tong University（上海交通大学）；GAIR；Alibaba Group（阿里巴巴集团）；University of Science and Technology of China（中国科学技术大学）；Shanghai Innovation Institute（上海创新研究院）
Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning
School of Computer Science and Engineering, Southeast University（计算机科学与工程学院，东南大学）；Key Laboratory of Computer Network and Information Integration (Southeast University), MoE, China（计算机网络与信息集成重点实验室（东南大学），教育部，中国）；School of Information and Physical Sciences, The University of Newcastle（信息与物理科学学院，新castle大学）
Tuning the Right Foundation Models is What you Need for Partial Label Learning
School of Computer Science and Engineering, Southeast University, Nanjing 210096, China（南京大学计算机科学与工程学院）；Key Lab. of Computer Network and Information Integration (Southeast University), MoE, China（计算机网络与信息集成重点实验室（东南大学））
