OrthKD: Extracting Generalized Clinical Knowledge from Heterogeneous Teachers for Lightweight Deployment

• URL: http://arxiv.org/abs/2607.25545v1
• Date: Tue, 28 Jul 2026 10:24:40 GMT
• Title: OrthKD: Extracting Generalized Clinical Knowledge from Heterogeneous Teachers for Lightweight Deployment
• Abstract summary: Multi-teacher knowledge distillation (KD) is a natural compression strategy, but existing approaches largely assume that all teachers provide equally trustworthy supervision.<n>We propose OrthKD, a selective-trust distillation framework that transfers full supervision from the strong CNN.<n>This design preserves local lesion precision, injects global structural context, and improves robustness to distribution shift.
• Score: 8.442590154864684
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deploying diabetic retinopathy (DR) screening models in primary care requires edge-efficient systems that remain accurate, safe, and reliable under domain shift. Multi-teacher knowledge distillation (KD) is a natural compression strategy, but existing approaches largely assume that all teachers provide equally trustworthy supervision. In our setting, this assumption fails: a strong CNN teacher (EfficientNet-B3, 0.876 QWK) and a weaker Transformer teacher (Swin-Base, 0.830 QWK) are complementary, yet the Transformer's logits can still mislead the student. We therefore propose OrthKD, a selective-trust distillation framework that transfers full supervision from the strong CNN, uses feature-only distillation from the weak ViT, and enforces orthogonality between teacher-specific student projections to encourage complementary rather than redundant evidence. This design preserves local lesion precision, injects global structural context, and improves robustness to distribution shift. On 132,049 retinal images, a 5.4M-parameter MobileNetV3 student reaches 0.885 QWK on EyePACS and improves zero-shot Messidor-2 performance from 0.507 to 0.728 QWK, while also achieving strong referral AUC and calibration. These results show that selectively distilling heterogeneous teachers can enable practical DR screening on resource-constrained devices.

Related papers

• When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning [45.79647925282674]
  On-policy self-distillation (OPSD) trains a student on its own rollouts using a privileged teacher.<n>Existing entropy-based OPD methods relax this uniformity by modulating token-level supervision with teacher entropy.<n>We propose Position-Weighted On-Policy Self-Distillation (PW-OPSD), which applies an increasing position weight while keeping the same student rollout, privileged teacher pass, and clipped forward-KL target as OPSD.
  arXiv  Detail & Related papers  (2026-05-20T18:14:03Z)
• Self-Distilled Agentic Reinforcement Learning [65.24201057390938]
  Self-Distilled Agentic Reinforcement Learning maps detached token-level signals into a sigmoid gate.<n>SDAR consistently outperforms hybrid RL--OPSD baselines across model scales.
  arXiv  Detail & Related papers  (2026-05-14T17:51:26Z)
• Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation [49.117085054884676]
  On-policy distillation trains a student model on its own rollouts using dense feedback from a stronger teacher.<n>We operationalize this principle through a trajectory-specific release rule.<n> Experimental results across strong-to-weak distillation tasks indicate that this release rule consistently outperforms standard full-trajectory OPD.
  arXiv  Detail & Related papers  (2026-05-13T15:05:30Z)
• Distillation Traps and Guards: A Calibration Knob for LLM Distillability [54.90137955363471]
  We propose a post-hoc calibration method that enables control over a teacher's distillability via reinforcement fine-tuning.<n>Our objective combines task utility, KL anchor, and across-tokenizer calibration reward.<n> Experiments show that students distilled from distillable teachers outperform SFT and KD baselines.
  arXiv  Detail & Related papers  (2026-04-21T01:22:35Z)
• The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation [67.26315138466312]
  We propose a calibration-aware OPD framework, CaOPD, that estimates empirical confidence from model rollouts.<n>Our findings highlight that capability distillation does not imply confidence, and that confidence should be treated as an essential objective in post-training.
  arXiv  Detail & Related papers  (2026-04-18T04:43:40Z)
• Reinforcement-aware Knowledge Distillation for LLM Reasoning [63.53679456364683]
  Reinforcement learning (RL) post-training has recently driven gains in long chain-of-thought reasoning large language models (LLMs)<n>Most existing knowledge distillation methods are designed for supervised fine-tuning (SFT), relying on fixed teacher traces or teacher-student Kullback-Leibler (KL) divergence-based regularization.<n>We propose RL-aware distillation (RLAD), which performs selective imitation during RL -- guiding the student toward the teacher only when it improves the current policy update.
  arXiv  Detail & Related papers  (2026-02-26T00:20:39Z)
• REDistill: Robust Estimator Distillation for Balancing Robustness and Efficiency [0.0]
  We introduce REDistill, a principled framework grounded in robust statistics.<n>Redistill replaces the standard KD objective with a power divergence loss, a generalization of KL divergence.<n>Experiments on CIFAR-100 and ImageNet-1k demonstrate that REDistill consistently improves student accuracy in diverse teacher-student architectures.
  arXiv  Detail & Related papers  (2026-02-04T15:50:53Z)
• Revisiting Cross-Architecture Distillation: Adaptive Dual-Teacher Transfer for Lightweight Video Models [23.54434747665913]
  Cross-Architecture Knowledge Distillation (CAKD) addresses this by transferring knowledge from ViTs to CNNs.<n>We propose a Dual-Teacher Knowledge Distillation framework that leverages both a heterogeneous ViT teacher and a homogeneous CNN teacher.<n>Our method consistently outperforms state-of-the-art distillation approaches.
  arXiv  Detail & Related papers  (2025-11-12T16:39:54Z)
• PLD: A Choice-Theoretic List-Wise Knowledge Distillation [12.52282972328311]
  We introduce "Plackett-Luce Distillation (PLD)", a weighted list-wise ranking loss.<n>PLD achieves consistent gains across diverse architectures and distillation objectives.
  arXiv  Detail & Related papers  (2025-06-14T15:31:54Z)
• Distilling Adversarial Robustness Using Heterogeneous Teachers [9.404102810698202]
  robustness can be transferred from an adversarially trained teacher to a student model using knowledge distillation. We develop a defense framework against adversarial attacks by distilling robustness using heterogeneous teachers. Experiments on classification tasks in both white-box and black-box scenarios demonstrate that DARHT achieves state-of-the-art clean and robust accuracies.
  arXiv  Detail & Related papers  (2024-02-23T19:55:13Z)
• On Self-Distilling Graph Neural Network [64.00508355508106]
  We propose the first teacher-free knowledge distillation method for GNNs, termed GNN Self-Distillation (GNN-SD) The method is built upon the proposed neighborhood discrepancy rate (NDR), which quantifies the non-smoothness of the embedded graph in an efficient way. We also summarize a generic GNN-SD framework that could be exploited to induce other distillation strategies.
  arXiv  Detail & Related papers  (2020-11-04T12:29:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.