Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation

• URL: http://arxiv.org/abs/2305.05010v1
• Date: Mon, 8 May 2023 19:31:09 GMT
• Title: Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation
• Authors: Rongzhi Zhang, Jiaming Shen, Tianqi Liu, Jialu Liu, Michael Bendersky, Marc Najork, Chao Zhang
• Abstract summary: Students learn to imitate the teacher by minimizing the KL divergence of its output distribution with the teacher's output distribution. We argue that such a learning objective is sub-optimal because there exists a discrepancy between the teacher's output distribution and the ground truth label distribution. We propose a novel knowledge distillation objective PTLoss by first representing the vanilla KL-based distillation loss function via a Maclaurin series and then perturbing the leading-order terms in this series.
• Score: 37.57793306258625
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge distillation is a popular technique to transfer knowledge from large teacher models to a small student model. Typically, the student learns to imitate the teacher by minimizing the KL divergence of its output distribution with the teacher's output distribution. In this work, we argue that such a learning objective is sub-optimal because there exists a discrepancy between the teacher's output distribution and the ground truth label distribution. Therefore, forcing the student to blindly imitate the unreliable teacher output distribution leads to inferior performance. To this end, we propose a novel knowledge distillation objective PTLoss by first representing the vanilla KL-based distillation loss function via a Maclaurin series and then perturbing the leading-order terms in this series. This perturbed loss implicitly transforms the original teacher into a proxy teacher with a distribution closer to the ground truth distribution. We establish the theoretical connection between this "distribution closeness" and the student model generalizability, which enables us to select the PTLoss's perturbation coefficients in a principled way. Extensive experiments on five datasets demonstrate PTLoss can significantly improve the distillation effectiveness for teachers of various scales.

Related papers

• Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models [62.5501109475725]
  Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. This paper introduces Online Knowledge Distillation (OKD), where the teacher network integrates small online modules to concurrently train with the student model. OKD achieves or exceeds the performance of leading methods in various model architectures and sizes, reducing training time by up to fourfold.
  arXiv  Detail & Related papers  (2024-09-19T07:05:26Z)
• Knowledge Distillation with Refined Logits [31.205248790623703]
  We introduce Refined Logit Distillation (RLD) to address the limitations of current logit distillation methods. Our approach is motivated by the observation that even high-performing teacher models can make incorrect predictions. Our method can effectively eliminate misleading information from the teacher while preserving crucial class correlations.
  arXiv  Detail & Related papers  (2024-08-14T17:59:32Z)
• Multi-Granularity Semantic Revision for Large Language Model Distillation [66.03746866578274]
  We propose a multi-granularity semantic revision method for LLM distillation. At the sequence level, we propose a sequence correction and re-generation strategy. At the token level, we design a distribution adaptive clipping Kullback-Leibler loss as the distillation objective function. At the span level, we leverage the span priors of a sequence to compute the probability correlations within spans, and constrain the teacher and student's probability correlations to be consistent.
  arXiv  Detail & Related papers  (2024-07-14T03:51:49Z)
• Unbiased Knowledge Distillation for Recommendation [66.82575287129728]
  Knowledge distillation (KD) has been applied in recommender systems (RS) to reduce inference latency. Traditional solutions first train a full teacher model from the training data, and then transfer its knowledge to supervise the learning of a compact student model. We find such a standard distillation paradigm would incur serious bias issue -- popular items are more heavily recommended after the distillation.
  arXiv  Detail & Related papers  (2022-11-27T05:14:03Z)
• Toward Student-Oriented Teacher Network Training For Knowledge Distillation [40.55715466657349]
  We propose a teacher training method SoTeacher which incorporates Lipschitz regularization and consistency regularization into ERM. Experiments on benchmark datasets using various knowledge distillation algorithms and teacher-student pairs confirm that SoTeacher can improve student accuracy consistently.
  arXiv  Detail & Related papers  (2022-06-14T07:51:25Z)
• Teacher's pet: understanding and mitigating biases in distillation [61.44867470297283]
  Several works have shown that distillation significantly boosts the student's overall performance. However, are these gains uniform across all data subgroups? We show that distillation can harm performance on certain subgroups. We present techniques which soften the teacher influence for subgroups where it is less reliable.
  arXiv  Detail & Related papers  (2021-06-19T13:06:25Z)
• Knowledge distillation via adaptive instance normalization [52.91164959767517]
  We propose a new knowledge distillation method based on transferring feature statistics from the teacher to the student. Our method goes beyond the standard way of enforcing the mean and variance of the student to be similar to those of the teacher. We show that our distillation method outperforms other state-of-the-art distillation methods over a large set of experimental settings.
  arXiv  Detail & Related papers  (2020-03-09T17:50:12Z)

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.