Related papers: Learning to Learn from APIs: Black-Box Data-Free M…
Federated learning (FL) is a decentralized collaborative machine learning (ML) technique. It provides a solution to the issues of isolated data islands and data privacy leakage in industrial ML practices. One major challenge in FL is…
Diffusion models (DMs) have demonstrated exceptional generative capabilities across various domains, including image, video, and so on. A key factor contributing to their effectiveness is the high quantity and quality of data used during…
Knowledge Distillation (KD) is a promising technique for reducing the high computational demand of large language models (LLMs). However, previous KD methods are primarily applied to white-box classification models or training small models…
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…
This article reviews meta-learning also known as learning-to-learn which seeks rapid and accurate model adaptation to unseen tasks with applications in highly automated AI, few-shot learning, natural language processing and robotics. Unlike…
Due to limitations in data quality, some essential visual tasks are difficult to perform independently. Introducing previously unavailable information to transfer informative dark knowledge has been a common way to solve such hard tasks.…
Pre-trained language models have been applied to various NLP tasks with considerable performance gains. However, the large model sizes, together with the long inference time, limit the deployment of such models in real-time applications.…
Data-Free Meta-Learning (DFML) aims to derive knowledge from a collection of pre-trained models without accessing their original data, enabling the rapid adaptation to new unseen tasks. Current methods often overlook the heterogeneity among…
While deep learning has achieved remarkable results on various applications, it is usually data hungry and struggles to learn over non-stationary data stream. To solve these two limits, the deep learning model should not only be able to…
The performance of federated learning in neural networks is generally influenced by the heterogeneity of the data distribution. For a well-performing global model, taking a weighted average of the local models, as done by most existing…
Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train…
In this paper, we propose a selfdistillation framework with meta learning(MetaSD) for knowledge graph completion with dynamic pruning, which aims to learn compressed graph embeddings and tackle the longtail samples. Specifically, we first…
Dataset distillation aims to distill the knowledge of a large-scale real dataset into small yet informative synthetic data such that a model trained on it performs as well as a model trained on the full dataset. Despite recent progress,…
Modern machine learning requires system designers to specify aspects of the learning pipeline, such as losses, architectures, and optimizers. Meta-learning, or learning-to-learn, instead aims to learn those aspects, and promises to unlock…
Federated learning enables the creation of a powerful centralized model without compromising data privacy of multiple participants. While successful, it does not incorporate the case where each participant independently designs its own…
Federated learning has attracted increasing attention to building models without accessing the raw user data, especially in healthcare. In real applications, different federations can seldom work together due to possible reasons such as…
Data-Free Knowledge Distillation (DFKD) is an advanced technique that enables knowledge transfer from a teacher model to a student model without relying on original training data. While DFKD methods have achieved success on smaller datasets…
The goal of data-free meta-learning is to learn useful prior knowledge from a collection of pre-trained models without accessing their training data. However, existing works only solve the problem in parameter space, which (i) ignore the…
Deep metric learning aims to transform input data into an embedding space, where similar samples are close while dissimilar samples are far apart from each other. In practice, samples of new categories arrive incrementally, which requires…
Recent studies pointed out that knowledge distillation (KD) suffers from two degradation problems, the teacher-student gap and the incompatibility with strong data augmentations, making it not applicable to training state-of-the-art models,…