More Like this

1. Estimating and Maximizing Mutual Information for Knowledge Distillation

   Shrivastava, Aman; Qi, Yanjun; Ordonez, Vicente (January 2023, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops)

   In this work, we propose Mutual Information Maximization Knowledge Distillation (MIMKD). Our method uses a contrastive objective to simultaneously estimate and maximize a lower bound on the mutual information of local and global feature representations between a teacher and a student network. We demonstrate through extensive experiments that this can be used to improve the performance of low capacity models by transferring knowledge from more performant but computationally expensive models. This can be used to produce better models that can be run on devices with low computational resources. Our method is flexible, we can distill knowledge from teachers with arbitrary network architectures to arbitrary student networks. Our empirical results show that MIMKD outperforms competing approaches across a wide range of student-teacher pairs with different capacities, with different architectures, and when student networks are with extremely low capacity. We are able to obtain 74.55% accuracy on CIFAR100 with a ShufflenetV2 from a baseline accuracy of 69.8% by distilling knowledge from ResNet-50. On Imagenet we improve a ResNet-18 network from 68.88% to 70.32% accuracy (1.44%+) using a ResNet-34 teacher network. 

   more » « less
2. Cooperative Knowledge Distillation: A Learner Agnostic Approach

   https://doi.org/10.1609/aaai.v38i13.29322  

   Livanos, Michael; Davidson, Ian; Wong, Stephen (March 2024, Proceedings of the AAAI Conference on Artificial Intelligence)

   Knowledge distillation is a simple but powerful way to transfer knowledge between a teacher model to a student model. Existing work suffers from at least one of the following key limitations in terms of direction and scope of transfer which restrict its use: all knowledge is transferred from teacher to student regardless of whether or not that knowledge is useful, the student is the only one learning in this exchange, and typically distillation transfers knowledge only from a single teacher to a single student. We formulate a novel form of knowledge distillation in which many models can act as both students and teachers which we call cooperative distillation. The models cooperate as follows: a model (the student) identifies specific deficiencies in it's performance and searches for another model (the teacher) who encodes learned knowledge into instructional virtual instances via counterfactual instance generation. Because different models may have different strengths and weaknesses, all models can act as either students or teachers (cooperation) when appropriate and only distill knowledge in areas specific to their strengths (focus). Since counterfactuals as a paradigm are not tied to any specific algorithm, we can use this method to distill knowledge between learners of different architectures, algorithms, and even feature spaces. We demonstrate our approach not only outperforms baselines such as transfer learning, self-supervised learning, and multiple knowledge distillation algorithms on several datasets, but it can also be used in settings where the aforementioned techniques cannot. 

   more » « less
3. Quantifying Knowledge Distillation using Partial Information Decomposition

   Dissanayake, Pasan; Hamman, Faisal; Halder, Barproda; Sucholutsky, Ilia; Zhang, Qiuyi; Dutta, Sanghamitra (May 2025, Proceedings of Machine Learning Research)

   Knowledge distillation deploys complex machine learning models in resource-constrained environments by training a smaller student model to emulate internal representations of a complex teacher model. However, the teacher’s representations can also encode nuisance or additional information not relevant to the downstream task. Distilling such irrelevant information can actually impede the performance of a capacity-limited student model. This observation motivates our primary question: What are the information-theoretic limits of knowledge distillation? To this end, we leverage Partial Information Decomposition to quantify and explain the transferred knowledge and knowledge left to distill for a downstream task. We theoretically demonstrate that the task-relevant transferred knowledge is succinctly captured by the measure of redundant information about the task between the teacher and student. We propose a novel multi-level optimization to incorporate redundant information as a regularizer, leading to our framework of Redundant Information Distillation (RID). RID leads to more resilient and effective distillation under nuisance teachers as it succinctly quantifies task-relevant knowledge rather than simply aligning student and teacher representations. 

   more » « less
4. HGAN: Hybrid generative adversarial network

   https://doi.org/10.3233/JIFS-201202  

   Iranmanesh, Seyed Mehdi; Nasrabadi, Nasser M. (April 2021, Journal of Intelligent & Fuzzy Systems)

   In this paper, we present a simple approach to train Generative Adversarial Networks (GANs) in order to avoid a mode collapse issue. Implicit models such as GANs tend to generate better samples compared to explicit models that are trained on tractable data likelihood. However, GANs overlook the explicit data density characteristics which leads to undesirable quantitative evaluations and mode collapse. To bridge this gap, we propose a hybrid generative adversarial network (HGAN) for which we can enforce data density estimation via an autoregressive model and support both adversarial and likelihood framework in a joint training manner which diversify the estimated density in order to cover different modes. We propose to use an adversarial network to transfer knowledge from an autoregressive model (teacher) to the generator (student) of a GAN model. A novel deep architecture within the GAN formulation is developed to adversarially distill the autoregressive model information in addition to simple GAN training approach. We conduct extensive experiments on real-world datasets (i.e., MNIST, CIFAR-10, STL-10) to demonstrate the effectiveness of the proposed HGAN under qualitative and quantitative evaluations. The experimental results show the superiority and competitiveness of our method compared to the baselines. 

   more » « less
5. Adaptive wavelet distillation from neural networks through interpretations

   Ha, Wooseok; Singh, Chandan; Lanusse, Francois; Upadhyayula, Srigokul; Yu, Bin (December 2021, Advances in neural information processing systems)

   Recent deep-learning models have achieved impressive prediction performance, but often sacrifice interpretability and computational efficiency. Interpretability is crucial in many disciplines, such as science and medicine, where models must be carefully vetted or where interpretation is the goal itself. Moreover, interpretable models are concise and often yield computational efficiency. Here, we propose adaptive wavelet distillation (AWD), a method which aims to distill information from a trained neural network into a wavelet transform. Specifically, AWD penalizes feature attributions of a neural network in the wavelet domain to learn an effective multi-resolution wavelet transform. The resulting model is highly predictive, concise, computationally efficient, and has properties (such as a multi-scale structure) which make it easy to interpret. In close collaboration with domain experts, we showcase how AWD addresses challenges in two real-world settings: cosmological parameter inference and molecular-partner prediction. In both cases, AWD yields a scientifically interpretable and concise model which gives predictive performance better than state-of-the-art neural networks. Moreover, AWD identifies predictive features that are scientifically meaningful in the context of respective domains. All code and models are released in a full-fledged package available on Github. 

   more » « less