Tensor Decomposition based Personalized Federated Learning

Federated learning (FL) is a new distributed machine learning framework that can achieve reliably collaborative training without collecting users' private data. However, due to FL's frequent communication and average aggregation strategy, they experience challenges scaling to statistical diversity data and large-scale models. In this paper, we propose a personalized FL framework, named Tensor Decomposition based Personalized Federated learning (TDPFed), in which we design a novel tensorized local model with tensorized linear layers and convolutional layers to reduce the communication cost. TDPFed uses a bi-level loss function to decouple personalized model optimization from the global model learning by controlling the gap between the personalized model and the tensorized local model. Moreover, an effective distributed learning strategy and two different model aggregation strategies are well designed for the proposed TDPFed framework. Theoretical convergence analysis and thorough experiments demonstrate that our proposed TDPFed framework achieves state-of-the-art performance while reducing the communication cost.

Constraining Pseudo-label in Self-training Unsupervised Domain Adaptation with Energy-based Model

Deep learning is usually data starved, and the unsupervised domain adaptation (UDA) is developed to introduce the knowledge in the labeled source domain to the unlabeled target domain. Recently, deep self-training presents a powerful means for UDA, involving an iterative process of predicting the target domain and then taking the confident predictions as hard pseudo-labels for retraining. However, the pseudo-labels are usually unreliable, thus easily leading to deviated solutions with propagated errors. In this paper, we resort to the energy-based model and constrain the training of the unlabeled target sample with an energy function minimization objective. It can be achieved via a simple additional regularization or an energy-based loss. This framework allows us to gain the benefits of the energy-based model, while retaining strong discriminative performance following a plug-and-play fashion. The convergence property and its connection with classification expectation minimization are investigated. We deliver extensive experiments on the most popular and large-scale UDA benchmarks of image classification as well as semantic segmentation to demonstrate its generality and effectiveness.

Unsupervised Domain Adaptation for Segmentation with Black-box Source Model

Unsupervised domain adaptation (UDA) has been widely used to transfer knowledge from a labeled source domain to an unlabeled target domain to counter the difficulty of labeling in a new domain. The training of conventional solutions usually relies on the existence of both source and target domain data. However, privacy of the large-scale and well-labeled data in the source domain and trained model parameters can become the major concern of cross center/domain collaborations. In this work, to address this, we propose a practical solution to UDA for segmentation with a black-box segmentation model trained in the source domain only, rather than original source data or a white-box source model. Specifically, we resort to a knowledge distillation scheme with exponential mixup decay (EMD) to gradually learn target-specific representations. In addition, unsupervised entropy minimization is further applied to regularization of the target domain confidence. We evaluated our framework on the BraTS 2018 database, achieving performance on par with white-box source model adaptation approaches.

Subtype-Aware Dynamic Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) has been successfully applied to transfer knowledge from a labeled source domain to target domains without their labels. Recently introduced transferable prototypical networks (TPN) further addresses class-wise conditional alignment. In TPN, while the closeness of class centers between source and target domains is explicitly enforced in a latent space, the underlying fine-grained subtype structure and the cross-domain within-class compactness have not been fully investigated. To counter this, we propose a new approach to adaptively perform a fine-grained subtype-aware alignment to improve performance in the target domain without the subtype label in both domains. The insight of our approach is that the unlabeled subtypes in a class have the local proximity within a subtype, while exhibiting disparate characteristics, because of different conditional and label shifts. Specifically, we propose to simultaneously enforce subtype-wise compactness and class-wise separation, by utilizing intermediate pseudo-labels. In addition, we systematically investigate various scenarios with and without prior knowledge of subtype numbers, and propose to exploit the underlying subtype structure. Furthermore, a dynamic queue framework is developed to evolve the subtype cluster centroids steadily using an alternative processing scheme. Experimental results, carried out with multi-view congenital heart disease data and VisDA and DomainNet, show the effectiveness and validity of our subtype-aware UDA, compared with state-of-the-art UDA methods.

Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives

Deep learning has become the method of choice to tackle real-world problems in different domains, partly because of its ability to learn from data and achieve impressive performance on a wide range of applications. However, its success usually relies on two assumptions: (i) vast troves of labeled datasets are required for accurate model fitting, and (ii) training and testing data are independent and identically distributed. Its performance on unseen target domains, thus, is not guaranteed, especially when encountering out-of-distribution data at the adaptation stage. The performance drop on data in a target domain is a critical problem in deploying deep neural networks that are successfully trained on data in a source domain. Unsupervised domain adaptation (UDA) is proposed to counter this, by leveraging both labeled source domain data and unlabeled target domain data to carry out various tasks in the target domain. UDA has yielded promising results on natural image processing, video analysis, natural language processing, time-series data analysis, medical image analysis, etc. In this review, as a rapidly evolving topic, we provide a systematic comparison of its methods and applications. In addition, the connection of UDA with its closely related tasks, e.g., domain generalization and out-of-distribution detection, has also been discussed. Furthermore, deficiencies in current methods and possible promising directions are highlighted.

AI Enlightens Wireless Communication: A Transformer Backbone for CSI Feedback

This paper is based on the background of the 2nd Wireless Communication Artificial Intelligence (AI) Competition (WAIC) which is hosted by IMT-2020(5G) Promotion Group 5G+AIWork Group, where the framework of the eigenvector-based channel state information (CSI) feedback problem is firstly provided. Then a basic Transformer backbone for CSI feedback referred to EVCsiNet-T is proposed. Moreover, a series of potential enhancements for deep learning based (DL-based) CSI feedback including i) data augmentation, ii) loss function design, iii) training strategy, and iv) model ensemble are introduced. The experimental results involving the comparison between EVCsiNet-T and traditional codebook methods over different channels are further provided, which show the advanced performance and a promising prospect of Transformer on DL-based CSI feedback problem.

ACT: Semi-supervised Domain-adaptive Medical Image Segmentation with Asymmetric Co-training

Unsupervised domain adaptation (UDA) has been vastly explored to alleviate domain shifts between source and target domains, by applying a well-performed model in an unlabeled target domain via supervision of a labeled source domain. Recent literature, however, has indicated that the performance is still far from satisfactory in the presence of significant domain shifts. Nonetheless, delineating a few target samples is usually manageable and particularly worthwhile, due to the substantial performance gain. Inspired by this, we aim to develop semi-supervised domain adaptation (SSDA) for medical image segmentation, which is largely underexplored. We, thus, propose to exploit both labeled source and target domain data, in addition to unlabeled target data in a unified manner. Specifically, we present a novel asymmetric co-training (ACT) framework to integrate these subsets and avoid the domination of the source domain data. Following a divide-and-conquer strategy, we explicitly decouple the label supervisions in SSDA into two asymmetric sub-tasks, including semi-supervised learning (SSL) and UDA, and leverage different knowledge from two segmentors to take into account the distinction between the source and target label supervisions. The knowledge learned in the two modules is then adaptively integrated with ACT, by iteratively teaching each other, based on the confidence-aware pseudo-label. In addition, pseudo label noise is well-controlled with an exponential MixUp decay scheme for smooth propagation. Experiments on cross-modality brain tumor MRI segmentation tasks using the BraTS18 database showed, even with limited labeled target samples, ACT yielded marked improvements over UDA and state-of-the-art SSDA methods and approached an "upper bound" of supervised joint training.

Tagged-MRI Sequence to Audio Synthesis via Self Residual Attention Guided Heterogeneous Translator

Understanding the underlying relationship between tongue and oropharyngeal muscle deformation seen in tagged-MRI and intelligible speech plays an important role in advancing speech motor control theories and treatment of speech related-disorders. Because of their heterogeneous representations, however, direct mapping between the two modalities -- i.e., two-dimensional (mid-sagittal slice) plus time tagged-MRI sequence and its corresponding one-dimensional waveform -- is not straightforward. Instead, we resort to two-dimensional spectrograms as an intermediate representation, which contains both pitch and resonance, from which to develop an end-to-end deep learning framework to translate from a sequence of tagged-MRI to its corresponding audio waveform with limited dataset size.~Our framework is based on a novel fully convolutional asymmetry translator with guidance of a self residual attention strategy to specifically exploit the moving muscular structures during speech.~In addition, we leverage a pairwise correlation of the samples with the same utterances with a latent space representation disentanglement strategy.~Furthermore, we incorporate an adversarial training approach with generative adversarial networks to offer improved realism on our generated spectrograms.~Our experimental results, carried out with a total of 63 tagged-MRI sequences alongside speech acoustics, showed that our framework enabled the generation of clear audio waveforms from a sequence of tagged-MRI, surpassing competing methods. Thus, our framework provides the great potential to help better understand the relationship between the two modalities.

Sparse Federated Learning with Hierarchical Personalization Models

Federated learning (FL) is widely used in the Internet of Things (IoT), wireless networks, mobile devices, autonomous vehicles, and human activity due to its excellent potential in cybersecurity and privacy security. Though FL method can achieve privacy-safe and reliable collaborative training without collecting users' privacy data, it suffers from many challenges during both training and deployment. The main challenges in FL are the difficulty of non-i.i.d co-training data caused by the statistical diversity of the data from various participants, and the difficulty of application deployment caused by the excessive traffic volume and long communication delay between the central server and the client. To address these problems, we propose a sparse FL scheme with hierarchical personalization models (sFedHP), which minimizes clients' loss functions including the properties of an approximated L1-norm and the hierarchical proximal mapping, to reduce the communicational and computational loads required in the network, while improving the performance on statistical diversity data. Convergence analysis shows that the sparse constraint in sFedHP only reduces the convergence speed to a small extent, while the communication cost is greatly reduced. Experimentally, we demonstrate the benefits of this sparse hierarchical personalization architecture compared with the client-edge-cloud hierarchical FedAvg and the state-of-the-art personalization methods.

Bathymetry Inversion using a Deep-Learning-Based Surrogate for Shallow Water Equations Solvers

River bathymetry is critical for many aspects of water resources management. We propose and demonstrate a bathymetry inversion method using a deep-learning-based surrogate for shallow water equations solvers. The surrogate uses the convolutional autoencoder with a shared-encoder, separate-decoder architecture. It encodes the input bathymetry and decodes to separate outputs for flow-field variables. A gradient-based optimizer is used to perform bathymetry inversion with the trained surrogate. Two physically-based constraints on both bed elevation value and slope have to be added as inversion loss regularizations to obtain usable inversion results. Using the "L-curve" criterion, a heuristic approach was proposed to determine the regularization parameters. Both the surrogate model and the inversion algorithm show good performance. We found the bathymetry inversion process has two distinctive stages, which resembles the sculptural process of initial broad-brush calving and final detailing. The inversion loss due to flow prediction error reaches its minimum in the first stage and remains almost constant afterward. The bed elevation value and slope regularizations play the dominant role in the second stage in selecting the most probable solution. We also found the surrogate architecture (whether with both velocity and water surface elevation or velocity only as outputs) does not show significant impact on inversion result.