The representation gap between teacher and student is an emerging topic in knowledge distillation (KD). To reduce the gap and improve the performance, current methods often resort to complicated training schemes, loss functions, and feature alignments, which are task-specific and feature-specific. In this paper, we state that the essence of these methods is to discard the noisy information and distill the valuable information in the feature, and propose a novel KD method dubbed DiffKD, to explicitly denoise and match features using diffusion models. Our approach is based on the observation that student features typically contain more noises than teacher features due to the smaller capacity of student model. To address this, we propose to denoise student features using a diffusion model trained by teacher features. This allows us to perform better distillation between the refined clean feature and teacher feature. Additionally, we introduce a light-weight diffusion model with a linear autoencoder to reduce the computation cost and an adaptive noise matching module to improve the denoising performance. Extensive experiments demonstrate that DiffKD is effective across various types of features and achieves state-of-the-art performance consistently on image classification, object detection, and semantic segmentation tasks. Code is available at https://github.com/hunto/DiffKD.

Despite the importance of social science knowledge for various stakeholders, measuring its diffusion into different domains remains a challenge. This study uses a novel text-based approach to measure the idea-level diffusion of social science knowledge from the research domain to the journalism and policy-making domains. By doing so, we expand the detection of knowledge diffusion beyond the measurements of direct references. Our study focuses on media effects theories as key research ideas in the field of communication science. Using 72,703 documents (2000-2019) from three domains (i.e., research, journalism, and policy-making) that mention these ideas, we count the mentions of these ideas in each domain, estimate their domain-specific contexts, and track and compare differences across domains and over time. Overall, we find that diffusion patterns and dynamics vary considerably between ideas, with some ideas diffusing between other domains, while others do not. Based on the embedding regression approach, we compare contextualized meanings across domains and find that the distances between research and policy are typically larger than between research and journalism. We also find that ideas largely shift roles across domains - from being the theories themselves in research to sense-making in news to applied, administrative use in policy. Over time, we observe semantic convergence mainly for ideas that are practically oriented. Our results characterize the cross-domain diffusion patterns and dynamics of social science knowledge at the idea level, and we discuss the implications for measuring knowledge diffusion beyond citations.

The representation gap between teacher and student is an emerging topic in knowledge distillation (KD). To reduce the gap and improve the performance, current methods often resort to complicated training schemes, loss functions, and feature alignments, which are task-specific and feature-specific. In this paper, we state that the essence of these methods is to discard the noisy information and distill the valuable information in the feature, and propose a novel KD method dubbed DiffKD, to explicitly denoise and match features using diffusion models. Our approach is based on the observation that student features typically contain more noises than teacher features due to the smaller capacity of student model. To address this, we propose to denoise student features using a diffusion model trained by teacher features.