paper-with-me

홈 › Papers

Multi-Teacher Ensemble Distillation: A Mathematical Framework for Probability-Domain Knowledge Aggregation

2026-01-14 · Aaron R. Flouro, Shawn P. Chadwick arxiv

Building on the probability-domain distillation framework of Sparse-KD, we develop an axiomatic, operator-theoretic framework for multi-teacher ensemble knowledge distillation. Rather than prescribing a specific aggregation formula, we define five core axioms governing valid knowledge aggregation operators, encompassing convexity, positivity, continuity, weight monotonicity, and temperature coherence. We prove the existence and non-uniqueness of operator families satisfying these axioms, establishing that multiple distinct aggregation mechanisms conform to the same foundational principles. Within this framework, we establish operator-agnostic guarantees showing that multi-teacher aggregation reduces both stochastic variance and systematic supervisory bias under heterogeneous teachers, while providing Jensen-type bounds, log-loss guarantees, and safety attenuation properties. For aggregation operators linear in teacher weights, we further establish classical ensemble variance-reduction results under standard independence assumptions, with extensions to correlated-error regimes. The framework provides theoretical grounding for multi-teacher distillation from diverse frontier models while admitting multiple valid implementation strategies.

📄 PDF Abstract BibTeX arXiv:2601.09165

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation

Similar Papers 제목 키워드 기반

FEED: Feature-level Ensemble for Knowledge Distillation

2019-09-24 · SeongUk Park, Nojun Kwak

Knowledge Distillation (KD) aims to transfer knowledge in a teacher-student framework, by providing the predictions of the teacher network to the student network in the training stage to help the student network generali…

Knowledge Distillation

Unified and Effective Ensemble Knowledge Distillation

2022-04-01 · Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang

Ensemble knowledge distillation can extract knowledge from multiple teacher models and encode it into a single student model. Many existing methods learn and distill the student model on labeled data only. However, the t…

Knowledge DistillationTransfer Learning

The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learning

2019-05-31 · Bonggun Shin, Hao Yang, Jinho D. Choi

Recent advances in deep learning have facilitated the demand of neural models for real applications. In practice, these applications often need to be deployed with limited resources while keeping high accuracy. This pape…

Document ClassificationEnsemble LearningSentiment AnalysisWord Embeddings

PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation

2022-11-11 · Lianshang Cai, Linhao Zhang, Dehong Ma, Jun Fan 외

Pre-trained language models have become a crucial part of ranking systems and achieved very impressive effects recently. To maintain high performance while keeping efficient computations, knowledge distillation is widely…

Knowledge Distillation

Recursive Meta-Distillation: An Axiomatic Framework for Iterative Knowledge Refinement

2026-01-19 · Aaron R. Flouro, Shawn P. Chadwick arxiv

Recent work in probability-domain knowledge distillation has established axiomatic frameworks for temperature scaling, multi-teacher aggregation, and bias-variance trade-offs in single-stage settings. However, the mathem…

Knowledge Distillation