Knowledge distillation in machine learning is the process of transferring knowledge from a large model called the teacher to a smaller model called the student. Knowledge distillation is one of the techniques to compress the large network (teacher) to a smaller network (student) that can be deployed in small devices such as mobile phones. When the network size gap between the teacher and student increases, the performance of the student network decreases. To solve this problem, an intermediate model is employed between the teacher model and the student model known as the teaching assistant model, which in turn bridges the gap between the teacher and the student. In this research, we have shown that using multiple teaching assistant models, the student model (the smaller model) can be further improved. We combined these multiple teaching assistant models using weighted ensemble learning where we have used a differential evaluation optimization algorithm to generate the weight values.
LIB-KD: Teaching Inductive Bias for Efficient Vision Transformer Distillation and Compression
Department of Electrical Engineering Indian Institute of Technology Delhi（电子工程系印度理工学院德里）；Yogananda School of AI, Computers and Data Sciences（Yoganananda人工智能、计算机与数据科学学院）
Washington State University（华盛顿州立大学）；DeepMind（深度思维）；D.E. Shaw（德劭集团）
Despite the fact that deep neural networks are powerful models and achieve appealing results on many tasks, they are too large to be deployed on edge devices like smartphones or embedded sensor nodes. There have been efforts to compress these networks, and a popular method is knowledge distillation, where a large (teacher) pre-trained network is used to train a smaller (student) network. However, in this paper, we show that the student network performance degrades when the gap between student and teacher is large. Given a fixed student network, one cannot employ an arbitrarily large teacher, o…
Knowledge distillation is a standard teacher-student learning framework to train a light-weight student network under the guidance of a well-trained large teacher network. As an effective teaching strategy, interactive teaching has been widely employed at school to motivate students, in which teachers not only provide knowledge but also give constructive feedback to students upon their responses, to improve their learning performance. In this work, we propose an InterActive Knowledge Distillation (IAKD) scheme to leverage the interactive teaching strategy for efficient knowledge distillation. …
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Snap Inc.（色拉布公司）
Graph Neural Networks (GNNs) are popular for graph machine learning and have shown great results on wide node classification tasks. Yet, they are less popular for practical deployments in the industry owing to their scalability challenges incurred by data dependency. Namely, GNN inference depends on neighbor nodes multiple hops away from the target, and fetching them burdens latency-constrained applications. Existing inference acceleration methods like pruning and quantization can speed up GNNs by reducing Multiplication-and-ACcumulation (MAC) operations, but the improvements are limited given…
Teaching MLPs to Master Heterogeneous Graph-Structured Knowledge for Efficient and Accurate Inference
State Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学）；School of Information Technology and Electrical Engineering, The University of Queensland（信息科技与电气工程学院，昆士兰大学）
Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image Recognition
Northwestern Polytechnical University（西北工业大学）；Xijing Hospital, The Fourth Military Medical University（第四军医大学西京医院）；Beijing Technology And Business University（北京工商大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Nankai University（南开大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）
As virtual assistants have become more diverse and specialized, so has the demand for application or brand-specific wake words. However, the wake-word-specific datasets typically used to train wake-word detectors are costly to create. In this paper, we explore two techniques to leverage acoustic modeling data for large-vocabulary speech recognition to improve a purpose-built wake-word detector: transfer learning and knowledge distillation. We also explore how these techniques interact with time-synchronous training targets to improve detection latency. Experiments are presented on the open-sou…
Knowledge distillation usually transfers the knowledge from a pre-trained cumbersome teacher network to a compact student network, which follows the classical teacher-teaching-student paradigm. Based on this paradigm, previous methods mostly focus on how to efficiently train a better student network for deployment. Different from the existing practices, in this paper, we propose a novel student-helping-teacher formula, Teacher Evolution via Self-Knowledge Distillation (TESKD), where the target teacher (for deployment) is learned with the help of multiple hierarchical students by sharing the st…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
Ensemble knowledge distillation can extract knowledge from multiple teacher models and encode it into a single student model. Many existing methods learn and distill the student model on labeled data only. However, the teacher models are usually learned on the same labeled data, and their predictions have high correlations with groudtruth labels. Thus, they cannot provide sufficient knowledge complementary to task labels for student teaching. Distilling on unseen unlabeled data has the potential to enhance the knowledge transfer from the teachers to the student. In this paper, we propose a uni…
Introductory hands-on courses such as our smartphone-based coding course, SuaCode require a lot of support for students to accomplish learning goals. Online environments make it even more difficult to get assistance especially more recently because of COVID-19. Given the multilingual context of SuaCode students - learners across 42 African countries that are mostly Anglophone or Francophone - in this work, we developed a bilingual Artificial Intelligence (AI) Teaching Assistant (TA) - Kwame - that provides answers to students' coding questions from SuaCode courses in English and French. Kwame …
T-LLM: Teaching Large Language Models to Forecast Time Series via Temporal Distillation
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）；School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）
LLM-to-Flow Distillation: Teaching Natural Language Goals to Scientific Generators
ETH Zurich（苏黎世联邦理工学院）；ETH AI Center（苏黎世联邦理工学院人工智能中心）；Technische Universität Wien（维也纳技术大学）；AITHYRA；University of Pennsylvania（宾夕法尼亚大学）；University of Oxford（牛津大学）
Using huge training datasets can be costly and inconvenient. This article explores various data distillation techniques that can reduce the amount of data required to successfully train deep networks. Inspired by recent ideas, we suggest new data distillation techniques based on generative teaching networks, gradient matching, and the Implicit Function Theorem. Experiments with the MNIST image classification problem show that the new methods are computationally more efficient than previous ones and allow to increase the performance of models trained on distilled data.
