2023-03-22 更新
FedMAE: Federated Self-Supervised Learning with One-Block Masked Auto-Encoder
Authors:Nan Yang, Xuanyu Chen, Charles Z. Liu, Dong Yuan, Wei Bao, Lizhen Cui
Latest federated learning (FL) methods started to focus on how to use unlabeled data in clients for training due to users’ privacy concerns, high labeling costs, or lack of expertise. However, current Federated Semi-Supervised/Self-Supervised Learning (FSSL) approaches fail to learn large-scale images because of the limited computing resources of local clients. In this paper, we introduce a new framework FedMAE, which stands for Federated Masked AutoEncoder, to address the problem of how to utilize unlabeled large-scale images for FL. Specifically, FedMAE can pre-train one-block Masked AutoEncoder (MAE) using large images in lightweight client devices, and then cascades multiple pre-trained one-block MAEs in the server to build a multi-block ViT backbone for downstream tasks. Theoretical analysis and experimental results on image reconstruction and classification show that our FedMAE achieves superior performance compared to the state-of-the-art FSSL methods.
PDF
点此查看论文截图
eP-ALM: Efficient Perceptual Augmentation of Language Models
Authors:Mustafa Shukor, Corentin Dancette, Matthieu Cord
Large Language Models (LLMs) have so far impressed the world, with unprecedented capabilities that emerge in models at large scales. On the vision side, transformer models (i.e., ViT) are following the same trend, achieving the best performance on challenging benchmarks. With the abundance of such unimodal models, a natural question arises; do we need also to follow this trend to tackle multimodal tasks? In this work, we propose to rather direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception. Existing approaches for adapting pretrained models for vision-language tasks still rely on several key components that hinder their efficiency. In particular, they still train a large number of parameters, rely on large multimodal pretraining, use encoders (e.g., CLIP) trained on huge image-text datasets, and add significant inference overhead. In addition, most of these approaches have focused on Zero-Shot and In Context Learning, with little to no effort on direct finetuning. We investigate the minimal computational effort needed to adapt unimodal models for multimodal tasks and propose a new challenging setup, alongside different approaches, that efficiently adapts unimodal pretrained models. We show that by freezing more than 99\% of total parameters, training only one linear projection layer, and prepending only one trainable token, our approach (dubbed eP-ALM) significantly outperforms other baselines on VQA and Captioning across Image, Video, and Audio modalities, following the proposed setup. The code will be available here: https://github.com/mshukor/eP-ALM.
PDF Code: https://github.com/mshukor/eP-ALM