Tencent AI Lab（腾讯人工智能实验室）；University of Texas at Arlington（德克萨斯大学阿灵顿分校）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
Recently, the teacher-student knowledge distillation framework has demonstrated its potential in training Graph Neural Networks (GNNs). However, due to the difficulty of training over-parameterized GNN models, one may not easily obtain a satisfactory teacher model for distillation. Furthermore, the inefficient training process of teacher-student knowledge distillation also impedes its applications in GNN models. In this paper, we propose the first teacher-free knowledge distillation method for GNNs, termed GNN Self-Distillation (GNN-SD), that serves as a drop-in replacement of the standard training process. The method is built upon the proposed neighborhood discrepancy rate (NDR), which quantifies the non-smoothness of the embedded graph in an efficient way. Based on this metric, we propose the adaptive discrepancy retaining (ADR) regularizer to empower the transferability of knowledge that maintains high neighborhood discrepancy across GNN layers. We also summarize a generic GNN-SD framework that could be exploited to induce other distillation strategies. Experiments further prove the effectiveness and generalization of our approach, as it brings: 1) state-of-the-art GNN distillation performance with less training cost, 2) consistent and considerable performance enhancement for various popular backbones.
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Zhejiang University（浙江大学）
Researchers have recently proposed plenty of heterogeneous graph neural networks (HGNNs) due to the ubiquity of heterogeneous graphs in both academic and industrial areas. Instead of pursuing a more powerful HGNN model, in this paper, we are interested in devising a versatile plug-and-play module, which accounts for distilling relational knowledge from pre-trained HGNNs. To the best of our knowledge, we are the first to propose a HIgh-order RElational (HIRE) knowledge distillation framework on heterogeneous graphs, which can significantly boost the prediction performance regardless of model ar…
University of Electronic Science and Technology of China（电子科技大学）
Nowadays, Graph Neural Networks (GNNs) following the Message Passing paradigm become the dominant way to learn on graphic data. Models in this paradigm have to spend extra space to look up adjacent nodes with adjacency matrices and extra time to aggregate multiple messages from adjacent nodes. To address this issue, we develop a method called LinkDist that distils self-knowledge from connected node pairs into a Multi-Layer Perceptron (MLP) without the need to aggregate messages. Experiment with 8 real-world datasets shows the MLP derived from LinkDist can predict the label of a node without kn…
Graph Neural Networks (GNNs) have achieved state-of-the-art performance in node classification, regression, and recommendation tasks. GNNs work well when rich and high-quality connections are available. However, their effectiveness is often jeopardized in many real-world graphs in which node degrees have power-law distributions. The extreme case of this situation, where a node may have no neighbors, is called Strict Cold Start (SCS). SCS forces the prediction to rely completely on the node's own features. We propose Cold Brew, a teacher-student distillation approach to address the SCS and nois…
State University of New York at Binghamton（纽约州立大学宾汉姆顿分校）
Knowledge distillation (KD) transfers knowledge from a teacher network to a student by enforcing the student to mimic the outputs of the pretrained teacher on training data. However, data samples are not always accessible in many cases due to large data sizes, privacy, or confidentiality. Many efforts have been made on addressing this problem for convolutional neural networks (CNNs) whose inputs lie in a grid domain within a continuous space such as images and videos, but largely overlook graph neural networks (GNNs) that handle non-grid data with different topology structures within a discret…
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）
We study a new paradigm of knowledge transfer that aims at encoding graph topological information into graph neural networks (GNNs) by distilling knowledge from a teacher GNN model trained on a complete graph to a student GNN model operating on a smaller or sparser graph. To this end, we revisit the connection between thermodynamics and the behavior of GNN, based on which we propose Neural Heat Kernel (NHK) to encapsulate the geometric property of the underlying manifold concerning the architecture of GNNs. A fundamental and principled solution is derived by aligning NHKs on teacher and studen…
Indian Institute of Technology Kharagpur（印度理工学院卡哈拉格普尔分校）；Indo Korea Science and Technology Center（印韩科学技术中心）；Leibniz University of Hannover（莱布尼茨汉诺威大学）
In recent years, graph neural network (GNN) based approaches have emerged as a powerful technique to encode complex topological structure of crystal materials in an enriched representation space. These models are often supervised in nature and using the property-specific training data, learn relationship between crystal structure and different properties like formation energy, bandgap, bulk modulus, etc. Most of these methods require a huge amount of property-tagged data to train the system which may not be available for different properties. However, there is an availability of a huge amount …
Distilling neural networks into skipgram-level decision lists
Computational Linguistics and Psycholinguistics Research Center (CLiPS)（计算语言学与心理语言学研究中心（CLiPS））；University of Antwerp（安特卫普大学）；School of Computing and Information Systems, University of Melbourne（墨尔本大学计算与信息系统学院）
This paper addresses the trade-off between Accuracy and Transparency for deep learning applied to sports analytics. Neural nets achieve great predictive accuracy through deep learning, and are popular in sports analytics. But it is hard to interpret a neural net model and harder still to extract actionable insights from the knowledge implicit in it. Therefore, we built a simple and transparent model that mimics the output of the original deep learning model and represents the learned knowledge in an explicit interpretable way. Our mimic model is a linear model tree, which combines a collection…
Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
Machine learning applications to symbolic mathematics are becoming increasingly popular, yet there lacks a centralized source of real-world symbolic expressions to be used as training data. In contrast, the field of natural language processing leverages resources like Wikipedia that provide enormous amounts of real-world textual data. Adopting the philosophy of "mathematics as language," we bridge this gap by introducing a pipeline for distilling mathematical expressions embedded in Wikipedia into symbolic encodings to be used in downstream machine learning tasks. We demonstrate that a $\texti…
Recent advances in pre-training huge models on large amounts of text through self supervision have obtained state-of-the-art results in various natural language processing tasks. However, these huge and expensive models are difficult to use in practise for downstream tasks. Some recent efforts use knowledge distillation to compress these models. However, we see a gap between the performance of the smaller student models as compared to that of the large teacher. In this work, we leverage large amounts of in-domain unlabeled transfer data in addition to a limited amount of labeled training insta…
Current state-of-the-art Neural Architecture Search (NAS) methods neither efficiently scale to multiple hardware platforms, nor handle diverse architectural search-spaces. To remedy this, we present DONNA (Distilling Optimal Neural Network Architectures), a novel pipeline for rapid, scalable and diverse NAS, that scales to many user scenarios. DONNA consists of three phases. First, an accuracy predictor is built using blockwise knowledge distillation from a reference model. This predictor enables searching across diverse networks with varying macro-architectural parameters such as layer types …
Pre-trained transformers have recently clinched top spots in the gamut of natural language tasks and pioneered solutions to software engineering tasks. Even information retrieval has not been immune to the charm of the transformer, though their large size and cost is generally a barrier to deployment. While there has been much work in streamlining, caching, and modifying transformer architectures for production, here we explore a new direction: distilling a large pre-trained translation model into a lightweight bi-encoder which can be efficiently cached and queried. We argue from a probabilist…
University of Tübingen（蒂宾根大学）；MPI for Informatics（马克斯·普朗克信息学研究所）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Heidelberg（海德堡大学）
Recent advances have indicated the strengths of self-supervised pre-training for improving representation learning on downstream tasks. Existing works often utilize self-supervised pre-trained models by fine-tuning on downstream tasks. However, fine-tuning does not generalize to the case when one needs to build a customized model architecture different from the self-supervised model. In this work, we formulate a new knowledge distillation framework to transfer the knowledge from self-supervised pre-trained models to any other student network by a novel approach named Embedding Graph Alignment.…
Siemens AG, Corporate Technology（西门子公司企业技术部）；University of Munich（慕尼黑大学）
In recent years, many explanation methods have been proposed to explain individual classifications of deep neural networks. However, how to leverage the created explanations to improve the learning process has been less explored. As the privileged information, the explanations of a model can be used to guide the learning process of the model itself. In the community, another intensively investigated privileged information used to guide the training of a model is the knowledge from a powerful teacher model. The goal of this work is to leverage the self-explanation to improve the learning proces…
We propose an algorithm that compresses the critical information of a large dataset into compact addressable memories. These memories can then be recalled to quickly re-train a neural network and recover the performance (instead of storing and re-training on the full original dataset). Building upon the dataset distillation framework, we make a key observation that a shared common representation allows for more efficient and effective distillation. Concretely, we learn a set of bases (aka ``memories'') which are shared between classes and combined through learned flexible addressing functions …
Collecting large-scale data with clean labels for supervised training of neural networks is practically challenging. Although noisy labels are usually cheap to acquire, existing methods suffer a lot from label noise. This paper targets at the challenge of robust training at high label noise regimes. The key insight to achieve this goal is to wisely leverage a small trusted set to estimate exemplar weights and pseudo labels for noisy data in order to reuse them for supervised training. We present a holistic framework to train deep neural networks in a way that is highly invulnerable to label no…
Recent research explosion on Neural Radiance Field (NeRF) shows the encouraging potential to represent complex scenes with neural networks. One major drawback of NeRF is its prohibitive inference time: Rendering a single pixel requires querying the NeRF network hundreds of times. To resolve it, existing efforts mainly attempt to reduce the number of required sampled points. However, the problem of iterative sampling still exists. On the other hand, Neural Light Field (NeLF) presents a more straightforward representation over NeRF in novel view synthesis -- the rendering of a pixel amounts to o…
City University of Hong Kong（香港城市大学）；Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）；Chinese Academy of Sciences（中国科学院）
One-shot weight sharing methods have recently drawn great attention in neural architecture search due to high efficiency and competitive performance. However, weight sharing across models has an inherent deficiency, i.e., insufficient training of subnetworks in hypernetworks. To alleviate this problem, we present a simple yet effective architecture distillation method. The central idea is that subnetworks can learn collaboratively and teach each other throughout the training process, aiming to boost the convergence of individual models. We introduce the concept of prioritized path, which refer…
DREvo: Distilling Recalibrated Historical Experience for Harness Self-Evolution
Southeast University（东南大学）；Hong Kong University of Science and Technology（香港科技大学）；Zhejiang Normal University（浙江师范大学）；Zhejiang University of Technology（浙江工业大学）；Zhejiang University（浙江大学）
Attributes of sound inherent to objects can provide valuable cues to learn rich representations for object detection and tracking. Furthermore, the co-occurrence of audiovisual events in videos can be exploited to localize objects over the image field by solely monitoring the sound in the environment. Thus far, this has only been feasible in scenarios where the camera is static and for single object detection. Moreover, the robustness of these methods has been limited as they primarily rely on RGB images which are highly susceptible to illumination and weather changes. In this work, we present…
Classical reduced models are low-rank approximations using a fixed basis designed to achieve dimensionality reduction of large-scale systems. In this work, we introduce reduced deep networks, a generalization of classical reduced models formulated as deep neural networks. We prove depth separation results showing that reduced deep networks approximate solutions of parametrized hyperbolic partial differential equations with approximation error $ε$ with $\mathcal{O}(|\log(ε)|)$ degrees of freedom, even in the nonlinear setting where solutions exhibit shock waves. We also show that classical redu…
Facebook AI Research（脸书人工智能研究院）；École normale supérieure, PSL University（巴黎高等师范学院，巴黎文理研究大学）；Inria（法国国家信息与自动化研究所）
The task of information retrieval is an important component of many natural language processing systems, such as open domain question answering. While traditional methods were based on hand-crafted features, continuous representations based on neural networks recently obtained competitive results. A challenge of using such methods is to obtain supervised data to train the retriever model, corresponding to pairs of query and support documents. In this paper, we propose a technique to learn retriever models for downstream tasks, inspired by knowledge distillation, and which does not require anno…
Learn from A Rationalist: Distilling Intermediate Interpretable Rationales
Department of Computing Science, University of Alberta, Edmonton, Canada（阿尔伯塔大学计算机科学系，加拿大埃德蒙顿）；Alberta Machine Intelligence Institute, Edmonton, Canada（阿尔伯塔机器智能研究所，加拿大埃德蒙顿）
Deep Reinforcement Learning uses a deep neural network to encode a policy, which achieves very good performance in a wide range of applications but is widely regarded as a black box model. A more interpretable alternative to deep networks is given by neuro-fuzzy controllers. Unfortunately, neuro-fuzzy controllers often need a large number of rules to solve relatively simple tasks, making them difficult to interpret. In this work, we present an algorithm to distill the policy from a deep Q-network into a compact neuro-fuzzy controller. This allows us to train compact neuro-fuzzy controllers thr…
End-to-end training with back propagation is the standard method for training deep neural networks. However, as networks become deeper and bigger, end-to-end training becomes more challenging: highly non-convex models gets stuck easily in local optima, gradients signals are prone to vanish or explode during back-propagation, training requires computational resources and time. In this work, we propose to break away from the end-to-end paradigm in the context of Knowledge Distillation. Instead of distilling a model end-to-end, we propose to split it into smaller sub-networks - also called neighb…
A computationally expensive and memory intensive neural network lies behind the recent success of language representation learning. Knowledge distillation, a major technique for deploying such a vast language model in resource-scarce environments, transfers the knowledge on individual word representations learned without restrictions. In this paper, inspired by the recent observations that language representations are relatively positioned and have more semantic knowledge as a whole, we present a new knowledge distillation objective for language representation learning that transfers the conte…
University of Electronic Science and Technology of China（电子科技大学）
The technology for Visual Odometry (VO) that estimates the position and orientation of the moving object through analyzing the image sequences captured by on-board cameras, has been well investigated with the rising interest in autonomous driving. This paper studies monocular VO from the perspective of Deep Learning (DL). Unlike most current learning-based methods, our approach, called DeepAVO, is established on the intuition that features contribute discriminately to different motion patterns. Specifically, we present a novel four-branch network to learn the rotation and translation by levera…
Single-Image-Super-Resolution (SISR) is a classical computer vision problem that has benefited from the recent advancements in deep learning methods, especially the advancements of convolutional neural networks (CNN). Although state-of-the-art methods improve the performance of SISR on several datasets, direct application of these networks for practical use is still an issue due to heavy computational load. For this purpose, recently, researchers have focused on more efficient and high-performing network structures. Information multi-distilling network (IMDN) is one of the highly efficient SIS…
Fudan University（复旦大学）；The University of Sydney（悉尼大学）
The message-passing mechanism helps Graph Neural Networks (GNNs) achieve remarkable results on various node classification tasks. Nevertheless, the recursive nodes fetching and aggregation in message-passing cause inference latency when deploying GNNs to large-scale graphs. One promising inference acceleration direction is to distill the GNNs into message-passing-free student multi-layer perceptrons (MLPs). However, the MLP student cannot fully learn the structure knowledge due to the lack of structure inputs, which causes inferior performance in the heterophily and inductive scenarios. To add…
