Papers › Relational Representation Distillation

Relational Representation Distillation

16 Jul 2024arXiv:2407.12073archive 2025-07-28

Nikolaos Giakoumoglou, Tania Stathaki

Knowledge distillation involves transferring knowledge from large, cumbersome teacher models to more compact student models. The standard approach minimizes the Kullback-Leibler (KL) divergence between the probabilistic outputs of a teacher and student network. However, this approach fails to capture important structural relationships in the teacher's internal representations. Recent advances have turned to contrastive learning objectives, but these methods impose overly strict constraints through instance-discrimination, forcing apart semantically similar samples even when they should maintain similarity. This motivates an alternative objective by which we preserve relative relationships between instances. Our method employs separate temperature parameters for teacher and student distributions, with sharper student outputs, enabling precise learning of primary relationships while preserving secondary similarities. We show theoretical connections between our objective and both InfoNCE loss and KL divergence. Experiments demonstrate that our method significantly outperforms existing knowledge distillation methods across diverse knowledge transfer tasks, achieving better alignment with teacher models, and sometimes even outperforms the teacher network.

PaperPDFCode

Code

giakoumoglou/distillers officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Computational EfficiencyContrastive LearningKnowledge DistillationSelf-Supervised LearningTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive LearningFocusInfoNCEKnowledge Distillation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections