Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher

• URL: http://arxiv.org/abs/2110.08532v1
• Date: Sat, 16 Oct 2021 09:49:43 GMT
• Title: Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher
• Authors: Mehdi Rezagholizadeh, Aref Jafari, Puneeth Salad, Pranav Sharma, Ali Saheb Pasand, Ali Ghodsi
• Abstract summary: Pro-KD technique defines a smoother training path for the student by following the training footprints of the teacher. We demonstrate our technique is quite effective in mitigating the capacity-gap problem and the checkpoint search problem.
• Score: 5.010360359434596
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: With ever growing scale of neural models, knowledge distillation (KD) attracts more attention as a prominent tool for neural model compression. However, there are counter intuitive observations in the literature showing some challenging limitations of KD. A case in point is that the best performing checkpoint of the teacher might not necessarily be the best teacher for training the student in KD. Therefore, one important question would be how to find the best checkpoint of the teacher for distillation? Searching through the checkpoints of the teacher would be a very tedious and computationally expensive process, which we refer to as the \textit{checkpoint-search problem}. Moreover, another observation is that larger teachers might not necessarily be better teachers in KD which is referred to as the \textit{capacity-gap} problem. To address these challenging problems, in this work, we introduce our progressive knowledge distillation (Pro-KD) technique which defines a smoother training path for the student by following the training footprints of the teacher instead of solely relying on distilling from a single mature fully-trained teacher. We demonstrate that our technique is quite effective in mitigating the capacity-gap problem and the checkpoint search problem. We evaluate our technique using a comprehensive set of experiments on different tasks such as image classification (CIFAR-10 and CIFAR-100), natural language understanding tasks of the GLUE benchmark, and question answering (SQuAD 1.1 and 2.0) using BERT-based models and consistently got superior results over state-of-the-art techniques.

Related papers

• Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling [81.00825302340984]
  We introduce Speculative Knowledge Distillation (SKD) to generate high-quality training data on-the-fly. In SKD, the student proposes tokens, and the teacher replaces poorly ranked ones based on its own distribution. We evaluate SKD on various text generation tasks, including translation, summarization, math, and instruction following.
  arXiv  Detail & Related papers  (2024-10-15T06:51:25Z)
• Linear Projections of Teacher Embeddings for Few-Class Distillation [14.99228980898161]
  Knowledge Distillation (KD) has emerged as a promising approach for transferring knowledge from a larger, more complex teacher model to a smaller student model. We introduce a novel method for distilling knowledge from the teacher's model representations, which we term Learning Embedding Linear Projections (LELP) Our experimental evaluation on large-scale NLP benchmarks like Amazon Reviews and Sentiment140 demonstrate the LELP is consistently competitive with, and typically superior to, existing state-of-the-art distillation algorithms for binary and few-class problems.
  arXiv  Detail & Related papers  (2024-09-30T16:07:34Z)
• Triplet Knowledge Distillation [73.39109022280878]
  In Knowledge Distillation, the teacher is generally much larger than the student, making the solution of the teacher likely to be difficult for the student to learn. To ease the mimicking difficulty, we introduce a triplet knowledge distillation mechanism named TriKD.
  arXiv  Detail & Related papers  (2023-05-25T12:12:31Z)
• 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)
• Gradient Knowledge Distillation for Pre-trained Language Models [21.686694954239865]
  We propose Gradient Knowledge Distillation (GKD) to incorporate the gradient alignment objective into the distillation process. Experimental results show that GKD outperforms previous KD methods regarding student performance.
  arXiv  Detail & Related papers  (2022-11-02T12:07:16Z)
• CES-KD: Curriculum-based Expert Selection for Guided Knowledge Distillation [4.182345120164705]
  This paper proposes a new technique called Curriculum Expert Selection for Knowledge Distillation (CES-KD) CES-KD is built upon the hypothesis that a student network should be guided gradually using stratified teaching curriculum. Specifically, our method is a gradual TA-based KD technique that selects a single teacher per input image based on a curriculum driven by the difficulty in classifying the image.
  arXiv  Detail & Related papers  (2022-09-15T21:02:57Z)
• 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)
• 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)
• Undistillable: Making A Nasty Teacher That CANNOT teach students [84.6111281091602]
  This paper introduces and investigates a concept called Nasty Teacher: a specially trained teacher network that yields nearly the same performance as a normal one. We propose a simple yet effective algorithm to build the nasty teacher, called self-undermining knowledge distillation.
  arXiv  Detail & Related papers  (2021-05-16T08:41:30Z)

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.