Dept. Computing Science & Alberta Machine Intelligence Institute (Amii), University of Alberta（计算科学系及阿尔伯塔人工智能研究所（Amii），阿尔伯塔大学）；Canada CIFAR AI Chair, Amii（加拿大CIFAR人工智能主席，Amii）
Knowledge distillation (KD) is a popular method of transferring knowledge from a large "teacher" model to a small "student" model. Previous work has explored various layer-selection strategies (e.g., forward matching and in-order random matching) for intermediate-layer matching in KD, where a student layer is forced to resemble a certain teacher layer. In this work, we revisit such layer-selection strategies and observe an intriguing phenomenon that layer-selection strategy does not matter (much) in intermediate-layer matching -- even seemingly nonsensical matching strategies such as reverse matching still result in surprisingly good student performance. We provide an interpretation for this phenomenon by examining the angles between teacher layers viewed from the student's perspective. Our work sheds light on KD practice, as layer-selection strategies may not be the main focus of KD system design, and vanilla forward matching works well in most setups.
Knowledge distillation (KD) is a highly promising method for mitigating the computational problems of pre-trained language models (PLMs). Among various KD approaches, Intermediate Layer Distillation (ILD) has been a de facto standard KD method with its performance efficacy in the NLP field. In this paper, we find that existing ILD methods are prone to overfitting to training datasets, although these methods transfer more information than the original KD. Next, we present the simple observations to mitigate the overfitting of ILD: distilling only the last Transformer layer and conducting ILD on…
Knowledge distillation is the procedure of transferring "knowledge" from a large model (the teacher) to a more compact one (the student), often being used in the context of model compression. When both models have the same architecture, this procedure is called self-distillation. Several works have anecdotally shown that a self-distilled student can outperform the teacher on held-out data. In this work, we systematically study self-distillation in a number of settings. We first show that even with a highly accurate teacher, self-distillation allows a student to surpass the teacher in all cases…
Knowledge Distillation (KD) has recently emerged as a popular method for compressing neural networks. In recent studies, generalized distillation methods that find parameters and architectures of student models at the same time have been proposed. Still, this search method requires a lot of computation to search for architectures and has the disadvantage of considering only convolutional blocks in their search space. This paper introduces a new algorithm, coined as Trust Region Aware architecture search to Distill knowledge Effectively (TRADE), that rapidly finds effective student architecture…
Singapore University of Technology and Design (SUTD)（新加坡科技设计大学）
This work investigates the compatibility between label smoothing (LS) and knowledge distillation (KD). Contemporary findings addressing this thesis statement take dichotomous standpoints: Muller et al. (2019) and Shen et al. (2021b). Critically, there is no effort to understand and resolve these contradictory findings, leaving the primal question -- to smooth or not to smooth a teacher network? -- unanswered. The main contributions of our work are the discovery, analysis and validation of systematic diffusion as the missing concept which is instrumental in understanding and resolving these con…
University of Science and Technology of China（中国科学技术大学）；Alibaba Group（阿里巴巴集团）；University of Southern California（南加州大学）；University of Sydney（悉尼大学）
Knowledge Distillation (KD) is a popular technique to transfer knowledge from a teacher model or ensemble to a student model. Its success is generally attributed to the privileged information on similarities/consistency between the class distributions or intermediate feature representations of the teacher model and the student model. However, directly pushing the student model to mimic the probabilities/features of the teacher model to a large extent limits the student model in learning undiscovered knowledge/features. In this paper, we propose a novel inheritance and exploration knowledge dis…
National University of Sciences and Technology（国家科技大学）；School of Electrical Engineering and Computer Science（电子工程与计算机科学学院）；National Center of Artificial Intelligence（国家人工智能中心）
One of the key differences between the learning mechanism of humans and Artificial Neural Networks (ANNs) is the ability of humans to learn one task at a time. ANNs, on the other hand, can only learn multiple tasks simultaneously. Any attempts at learning new tasks incrementally cause them to completely forget about previous tasks. This lack of ability to learn incrementally, called Catastrophic Forgetting, is considered a major hurdle in building a true AI system. In this paper, our goal is to isolate the truly effective existing ideas for incremental learning from those that only work under …
National University of Singapore（新加坡国立大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Knowledge Distillation (KD) aims to distill the knowledge of a cumbersome teacher model into a lightweight student model. Its success is generally attributed to the privileged information on similarities among categories provided by the teacher model, and in this sense, only strong teacher models are deployed to teach weaker students in practice. In this work, we challenge this common belief by following experimental observations: 1) beyond the acknowledgment that the teacher can improve the student, the student can also enhance the teacher significantly by reversing the KD procedure; 2) a poo…
Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA（多模态人工智能系统国家重点实验室，中科院自动化所）；School of Artificial Intelligence, UCAS（中国科学技术大学人工智能学院）；Fudan University（复旦大学）；Independent Researcher（独立研究者）
Adversarial training is one effective approach for training robust deep neural networks against adversarial attacks. While being able to bring reliable robustness, adversarial training (AT) methods in general favor high capacity models, i.e., the larger the model the better the robustness. This tends to limit their effectiveness on small models, which are more preferable in scenarios where storage or computing resources are very limited (e.g., mobile devices). In this paper, we leverage the concept of knowledge distillation to improve the robustness of small models by distilling from adversari…
Knowledge Distillation (KD) aims at transferring the knowledge of a well-performed neural network (the {\it teacher}) to a weaker one (the {\it student}). A peculiar phenomenon is that a more accurate model doesn't necessarily teach better, and temperature adjustment can neither alleviate the mismatched capacity. To explain this, we decompose the efficacy of KD into three parts: {\it correct guidance}, {\it smooth regularization}, and {\it class discriminability}. The last term describes the distinctness of {\it wrong class probabilities} that the teacher provides in KD. Complex teachers tend …
Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
Institute of Neuroscience（神经科学研究所）；Key Laboratory of Brain Cognition（脑认知重点实验室）；Brain-inspired Intelligence Technology（脑启发智能技术）；Center for Excellence in Brain Science（脑科学卓越中心）；Intelligence Technology（智能技术）；Chinese Academy of Sciences（中国科学院）；Shanghai, China（上海中国）
