Temporal Knowledge Distillation for on-device Audio Classification

Current Knowledge Distillation (KD) methods for semantic segmentation often guide the student to mimic the teacher's structured information generated from individual data samples. However, they ignore the global semantic relations among pixels across various images that are valuable for KD. This paper proposes a novel Cross-Image Relational KD (CIRKD), which focuses on transferring structured pixel-to-pixel and pixel-to-region relations among the whole images. The motivation is that a good teacher network could construct a well-structured feature space in terms of global pixel dependencies. CIRKD makes the student mimic better structured semantic relations from the teacher, thus improving the segmentation performance. Experimental results over Cityscapes, CamVid and Pascal VOC datasets demonstrate the effectiveness of our proposed approach against state-of-the-art distillation methods. The code is available at https://github.com/winycg/CIRKD.

As deep learning models are widely applied across various domains, a critical challenge is how to compress models while maintaining high reasoning capability. Knowledge distillation, an effective technique for model compression, has been used to enhance the performance of lightweight models. However, traditional distillation methods are limited when dealing with complex reasoning tasks. Reinforcement learning (RL) offers a novel approach to knowledge distillation by optimizing the reasoning strategies of teacher models, generating more efficient decision paths, and providing more valuable learning content for student models. This paper reviews the latest advancements in combining reinforcement learning with knowledge distillation, focusing on policy distillation, value function distillation, and dynamic reward-guided distillation methods. It also discusses the challenges faced by RL-driven distillation, such as simplifying complex strategies, addressing temporal dependencies, and balancing exploration and exploitation, and suggests possible solutions. Finally, this paper explores the applications of RL-driven knowledge distillation in fields such as game AI, robotic control, and dialogue systems, and outlines future research directions, including automated distillation, multimodal distillation, and challenges in federated learning.

Robust knowledge distillation based on feature variance against backdoored teacher model

A single model usually cannot learn all the appropriate features with limited data, thus leading to poor performance when test data are used. To improve model performance, we propose a teacher-student collaborative knowledge distillation (TSKD) method based on knowledge distillation and self-distillation. The method consists of two parts: learning in the teacher network and self-teaching in the student network. Learning in the teacher network allows the student network to use knowledge from the teacher network. Self-teaching in the student network is to build a multi-exit network based on self-distillation and provide deep features as supervised information for training. In the inference stage, we use ensembles to vote on the classification results of multiple sub-models in the student network. The experimental results demonstrate the superior performance of our method compared with a traditional knowledge distillation method and a self-distillation-based multi-exit network.

Knowledge Distillation (KD) aims to distill the dark knowledge of a high-powered teacher network into a student network, which can improve the capacity of student network and has been successfully applied to semantic segmentation. However, the standard knowledge distillation approaches merely represent the supervisory signal of teacher network as the dark knowledge, while ignoring the impact of network architecture during distillation. In this paper, we found that the student network with a more similar architecture against the teacher network obtains more performance gain from distillation. Therefore, a more generalized paradigm for knowledge distillation is to distill both the soft-label and the structure of the teacher network. We propose a novel Structural Distillation (SD) method which introduces the structural similarity constraints into vanilla knowledge distillation. We leverage Neural Architecture Search technique to search optimal student structure for semantic segmentation from a well-designed search space, which mimics the given teacher both in terms of soft-label and network structure. Experiment results make clear that our proposed method outperforms both the NAS with conventional Knowledge Distillation and human-designed methods, and achieves sota performance on the Cityscapes dataset under various platform-aware latency constraints. Furthermore, the best architecture discovered on Cityscapes also transfers well to the PASCAL VOC2012 dataset.

VFT: A versatile fine-tuning scheme based on feature distribution-aware knowledge distillation for lightweight convolutional neural networks

Knowledge distillation is a deep learning method that mimics the way that humans teach, i.e., a teacher network is used to guide the training of a student one. Knowledge distillation can generate an efficient student network to facilitate deployment in resource-constrained edge computing devices. Existing studies have typically mined knowledge from a teacher network and transferred it to a student one. The latter can only passively receive knowledge but cannot understand how the former acquires the knowledge, thus limiting the latter’s performance improvement. Inspired by the old Chinese saying “Give a man a fish and you feed him for a day; teach a man how to fish and you feed him for a lifetime,” this work proposes a Skill-transferring Knowledge Distillation (SKD) method to boost a student network’s ability to create new valuable knowledge. SKD consists of two main meta-learning networks: Teacher Behavior Teaching and Teacher Experience Teaching. The former captures the process of a teacher network’s learning behavior in the hidden layers and can predict the teacher network’s subsequent behavior based on previous ones. The latter models the optimal empirical knowledge of a teacher network’s output layer at each learning stage. With their help, a teacher network can provide its actions to a student one in the subsequent behavior and its optimal empirical knowledge in the current stage. The overall performance of SKD is verified through its application to multiple object recognition tasks and comparison with the state of the art.

DDDG: A dual bi-directional knowledge distillation method with generative self-supervised pre-training and its hardware implementation on SoC for ECG

Graph Neural Networks (GNNs) have shown remarkable effectiveness across various applications, but their computational complexity poses significant scalability challenges. To this end, GNN-to-MLP Knowledge Distillation (KD) methods transfer relational inductive biases from GNNs to MLPs, equipping MLPs with graph-aware capabilities that rival or even surpass those of their teacher GNNs. However, a theoretical foundation for understanding GNN-to-MLP KD is still missing. In this paper, we provide a theoretical analysis of how knowledge distillation unlocks the potential of MLPs for graph tasks from the perspective of training dynamics. We demonstrate that label alignment in KD fundamentally reshapes the Neural Tangent Kernel (NTK) matrix of student MLPs, enabling them to learn the teacher model’s implicit graph bias. We further investigate finer-grained distillation paradigms and reveal that conventional layer-wise output alignment fails to effectively align the deep-layer graph propagation outcomes. To address this, we propose Dual-Stream Aligned MLP (DA-MLP), which incorporates complementary graph filters in a dual-stream architecture. This approach simultaneously enhances feature space dimensionality for improved representation alignment and preserves graph signals across different frequency bands. Comprehensive experiments on seven benchmark datasets validate that DA-MLP can be seamlessly integrated into existing knowledge distillation frameworks for performance enhancements in both transductive and inductive settings.

Improving adversarial robustness using knowledge distillation guided by attention information bottleneck

The deep convolutional neural network has made significant progress in cloud detection. However, the compromise between having a compact model and high accuracy has always been a challenging task in cloud detection for large-scale remote sensing imagery. A promising method to tackle this problem is knowledge distillation, which usually lets the compact model mimic the cumbersome model’s output to get better generalization. However, vanilla knowledge distillation methods cannot properly distill the characteristics of clouds in remote sensing images. In this paper, we propose a novel self-attention knowledge distillation approach for compact and accurate cloud detection, named Bidirectional Self-Attention Distillation (Bi-SAD). Bi-SAD lets a model learn from itself without adding additional parameters or supervision. With bidirectional layer-wise features learning, the model can get a better representation of the cloud’s textural information and semantic information, so that the cloud’s boundaries become more detailed and the predictions become more reliable. Experiments on a dataset acquired by GaoFen-1 satellite show that our Bi-SAD has a great balance between compactness and accuracy, and outperforms vanilla distillation methods. Compared with state-of-the-art cloud detection models, the parameter size and FLOPs are reduced by 100 times and 400 times, respectively, with a small drop in accuracy.

Encoding facial expressions via action units (AUs) has been found to be effective in resolving the ambiguity issue among different expressions. Therefore, AU detection plays an important role for emotion analysis. While a number of AU detection methods have been proposed for common facial expressions, there is very limited study for micro-expression AU detection. Micro-expression AU detection is challenging because of the weakness of micro-expression appearance and the spontaneous characteristic leading to difficult collection, thus has small-scale datasets. In this paper, we focus on the micro-expression AU detection and expect to contribute to the community. To address above issues, a novel dual-view attentive similarity-preserving distillation method is proposed for robust micro-expression AU detection by leveraging massive facial expressions in the wild. Through such an attentive similarity-preserving distillation method, we break the domain shift problem and essential AU knowledge from common facial AUs is efficiently distilled. Furthermore, considering that the generalization ability of teacher network is important for knowledge distillation, a semi-supervised co-training approach is developed to construct a generalized teacher network for learning discriminative AU representation. Extensive experiments have demonstrated that our proposed knowledge distillation method can effectively distill and transfer the cross-domain knowledge for robust micro-expression AU detection.

A tucker decomposition based knowledge distillation for intelligent edge applications

We present Knowledge Distillation with Meta Learning (MetaDistil), a simple yet effective alternative to traditional knowledge distillation (KD) methods where the teacher model is fixed during training. We show the teacher network can learn to better transfer knowledge to the student network (i.e., learning to teach) with the feedback from the performance of the distilled student network in a meta learning framework. Moreover, we introduce a pilot update mechanism to improve the alignment between the inner-learner and meta-learner in meta learning algorithms that focus on an improved inner-learner. Experiments on various benchmarks show that MetaDistil can yield significant improvements compared with traditional KD algorithms and is less sensitive to the choice of different student capacity and hyperparameters, facilitating the use of KD on different tasks and models.

Knowledge distillation has become increasingly important in model compression. It boosts the performance of a miniaturized student network with the supervision of the output distribution and feature maps from a sophisticated teacher network. Some recent works introduce multi-teacher distillation to provide more supervision to the student network. However, the effectiveness of multi-teacher distillation methods are accompanied by costly computation resources. To tackle with both the efficiency and the effectiveness of knowledge distillation, we introduce the feature aggregation to imitate the multi-teacher distillation in the single-teacher distillation framework by extracting informative supervision from multiple teacher feature maps. Specifically, we introduce DFA, a two-stage Differentiable Feature Aggregation search method that motivated by DARTS in neural architecture search, to efficiently find the aggregations. In the first stage, DFA formulates the searching problem as a bi-level optimization and leverages a novel bridge loss, which consists of a student-to-teacher path and a teacher-to-student path, to find appropriate feature aggregations. The two paths act as two players against each other, trying to optimize the unified architecture parameters to the opposite directions while guaranteeing both expressivity and learnability of the feature aggregation simultaneously. In the second stage, DFA performs knowledge distillation with the derived feature aggregation. Experimental results show that DFA outperforms existing distillation methods on CIFAR-100 and CINIC-10 datasets under various teacher-student settings, verifying the effectiveness and robustness of the design.KeywordsKnowledge distillationFeature aggregationDifferentiable architecture search