Why does Knowledge Distillation Work? Rethink its Attention and Fidelity Mechanism

• URL: http://arxiv.org/abs/2405.00739v1
• Date: Tue, 30 Apr 2024 01:12:32 GMT
• Title: Why does Knowledge Distillation Work? Rethink its Attention and Fidelity Mechanism
• Authors: Chenqi Guo, Shiwei Zhong, Xiaofeng Liu, Qianli Feng, Yinglong Ma,
• Abstract summary: paradoxical studies indicate that closely replicating the teacher's behavior does not consistently improve student generalization. We propose this low-fidelity phenomenon as an underlying characteristic rather than a pathology when training KD.
• Score: 8.322293031346161
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Does Knowledge Distillation (KD) really work? Conventional wisdom viewed it as a knowledge transfer procedure where a perfect mimicry of the student to its teacher is desired. However, paradoxical studies indicate that closely replicating the teacher's behavior does not consistently improve student generalization, posing questions on its possible causes. Confronted with this gap, we hypothesize that diverse attentions in teachers contribute to better student generalization at the expense of reduced fidelity in ensemble KD setups. By increasing data augmentation strengths, our key findings reveal a decrease in the Intersection over Union (IoU) of attentions between teacher models, leading to reduced student overfitting and decreased fidelity. We propose this low-fidelity phenomenon as an underlying characteristic rather than a pathology when training KD. This suggests that stronger data augmentation fosters a broader perspective provided by the divergent teacher ensemble and lower student-teacher mutual information, benefiting generalization performance. These insights clarify the mechanism on low-fidelity phenomenon in KD. Thus, we offer new perspectives on optimizing student model performance, by emphasizing increased diversity in teacher attentions and reduced mimicry behavior between teachers and student.

Related papers

• On student-teacher deviations in distillation: does it pay to disobey? [54.908344098305804]
  Knowledge distillation has been widely used to improve the test accuracy of a "student" network. Despite being trained to fit the teacher's probabilities, the student may not only significantly deviate from the teacher probabilities, but may also outdo the teacher in performance.
  arXiv  Detail & Related papers  (2023-01-30T14:25:02Z)
• Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation [70.92135839545314]
  We propose the dynamic prior knowledge (DPK), which integrates part of teacher's features as the prior knowledge before the feature distillation. Our DPK makes the performance of the student model positively correlated with that of the teacher model, which means that we can further boost the accuracy of students by applying larger teachers.
  arXiv  Detail & Related papers  (2022-06-13T11:52:13Z)
• Evaluation-oriented Knowledge Distillation for Deep Face Recognition [19.01023156168511]
  We propose a novel Evaluation oriented KD method (EKD) for deep face recognition to directly reduce the performance gap between the teacher and student models during training. EKD uses the commonly used evaluation metrics in face recognition, i.e., False Positive Rate (FPR) and True Positive Rate (TPR) as the performance indicator.
  arXiv  Detail & Related papers  (2022-06-06T02:49:40Z)
• Generalized Knowledge Distillation via Relationship Matching [53.69235109551099]
  Knowledge of a well-trained deep neural network (a.k.a. the "teacher") is valuable for learning similar tasks. Knowledge distillation extracts knowledge from the teacher and integrates it with the target model. Instead of enforcing the teacher to work on the same task as the student, we borrow the knowledge from a teacher trained from a general label space.
  arXiv  Detail & Related papers  (2022-05-04T06:49:47Z)
• Improved Knowledge Distillation via Adversarial Collaboration [2.373824287636486]
  Small student model is trained to exploit the knowledge of a large well-trained teacher model. Due to the capacity gap between the teacher and the student, the student's performance is hard to reach the level of the teacher. We propose an Adversarial Collaborative Knowledge Distillation (ACKD) method that effectively improves the performance of knowledge distillation.
  arXiv  Detail & Related papers  (2021-11-29T07:20:46Z)
• Learning to Teach with Student Feedback [67.41261090761834]
  Interactive Knowledge Distillation (IKD) allows the teacher to learn to teach from the feedback of the student. IKD trains the teacher model to generate specific soft target at each training step for a certain student. Joint optimization for both teacher and student is achieved by two iterative steps.
  arXiv  Detail & Related papers  (2021-09-10T03:01:01Z)
• Does Knowledge Distillation Really Work? [106.38447017262183]
  We show that while knowledge distillation can improve student generalization, it does not typically work as it is commonly understood. We identify difficulties in optimization as a key reason for why the student is unable to match the teacher.
  arXiv  Detail & Related papers  (2021-06-10T17:44:02Z)
• Reducing the Teacher-Student Gap via Spherical Knowledge Disitllation [67.75526580926149]
  Knowledge distillation aims at obtaining a compact and effective model by learning the mapping function from a much larger one. We investigate the capacity gap problem by study the gap of confidence between teacher and student. We find that the magnitude of confidence is not necessary for knowledge distillation and could harm the student performance if the student are forced to learn confidence.
  arXiv  Detail & Related papers  (2020-10-15T03:03:36Z)

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.