We investigate the mechanisms of self-distillation in multi-class classification, particularly in the context of linear probing with fixed feature extractors where traditional feature learning explanations do not apply. Our theoretical analysis reveals that multi-round self-distillation effectively performs label averaging among instances with high feature correlations, governed by the eigenvectors of the Gram matrix derived from input features. This process leads to clustered predictions and improved generalization, mitigating the impact of label noise by reducing the model's reliance on potentially corrupted labels. We establish conditions under which multi-round self-distillation achieves 100% population accuracy despite label noise. Furthermore, we introduce a novel, efficient single-round self-distillation method using refined partial labels from the teacher's top two softmax outputs, referred to as the PLL student model. This approach replicates the benefits of multi-round distillation in a single round, achieving comparable or superior performance--especially in high-noise scenarios--while significantly reducing computational cost.
In optimization for Machine learning (ML), it is typical that curvature-matrix (CM) estimates rely on an exponential average (EA) of local estimates (giving EA-CM algorithms). This approach has little principled justification, but is very often used in practice. In this paper, we draw a connection between EA-CM algorithms and what we call a "Wake of Quadratic regularized models". The outlined connection allows us to understand what EA-CM algorithms are doing from an optimization perspective. Generalizing from the established connection, we propose a new family of algorithms, "KL-Divergence Wak…
Rethinking Reverse KL as Adaptive Entropy Distillation
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；School of Science and Technology, Hong Kong Metropolitan University（香港都会大学科技学院）
Rethinking Data Distillation: Do Not Overlook Calibration
Texas A&M University（德州农工大学）；Zhejiang University（浙江大学）；Certik；University of Maryland, College Park（马里兰大学帕克分校）；Purdue University（普渡大学）；North Carolina State University（北卡罗来纳州立大学）
Rethinking Decoupled Knowledge Distillation: A Predictive Distribution Perspective
Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University（数据科学与人工智能系，香港理工大学）；Department of Computing, The Hong Kong Polytechnic University（计算系，香港理工大学）；The Hong Kong Polytechnic University Shenzhen Research Institute（香港理工大学深圳研究院）
Korea Advanced Institute of Science and Technology（韩国科学技术院）；Naver；AITRICS
Ensembles of deep neural networks have demonstrated superior performance, but their heavy computational cost hinders applying them for resource-limited environments. It motivates distilling knowledge from the ensemble teacher into a smaller student network, and there are two important design choices for this ensemble distillation: 1) how to construct the student network, and 2) what data should be shown during training. In this paper, we propose a weight averaging technique where a student with multiple subnetworks is trained to absorb the functional diversity of ensemble teachers, but then th…
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）
Rethinking Dataset Distillation: Hard Truths about Soft Labels
Vision and AI Lab, Indian Institute of Science, Bangalore（印度科学研究院视觉与人工智能实验室，班加罗尔）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；IIT Hyderabad（海得拉巴理工学院）
Rethinking Continual Experience Internalization for Self-Evolving LLM Agents
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院 Gallagher 学院）；School of Software, Beihang University（北航软件学院）；Meituan（美团）
FedRIR: Rethinking Information Representation in Federated Learning
Institute for Clarity in Documentation（文献清晰研究所）；Inria Paris-Rocquencourt（法国国家信息与自动化研究所巴黎-罗克伦古中心）；Rajiv Gandhi University（拉吉夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕尔默研究实验室）
UI-MOPD: Multi-Platform On-Policy Distillation for Unified GUI Agents
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Xiaomi（小米）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Zhejiang University（浙江大学）；Peng Cheng Laboratory（鹏城实验室）
