Remote sensing (RS) applications increasingly operate over distributed infrastructures that integrate space-airground- sea resources with edge intelligence, yet remains challenging to centralize due to geographic dispersion, cross-institution barriers and privacy regulations. Federated learning (FL), a promising privacy-preserving distributed learning paradigm, has garnered wide attention. However, the practical application of FL for RS encounters the issue of label noise stemming from inevitable annotation errors. In this work, we pioneer an early investigation of label noise in distributed RS tasks. We introduce the Federated Representation Optimal Matching (FedROM) framework, which guides robust representation alignment in the presence of noisy labels without requiring auxiliary data or transmitting extra sensitive information. Specifically, FedROM focuses on the robust local updating process, where clients first identify underlying noisy samples from the perspectives of both per-sample loss value and latent representation space. Subsequently, inspired by the optimal transport technique, we adaptively align the latent representations of identified noisy samples with their corresponding closest class centroids with the least representation matching distance, where class centroids are averaged by the latent representations of other relatively clean samples. This reduces the misleading effects caused by noisy samples and guides the model to capture more robust semantic features in the latent representation space. Theoretical analysis proves the robustness and convergence of FedROM. Extensive experiments on two real-world distributed RS datasets covering multi-source domains and varying label noise rates demonstrate the robustness of FedROM against eighteen baseline methods. Meanwhile, FedROM also surpasses its counterparts in conditions of no label noise, narrowing the gap with the centralized training. To facilitate related communities, our code is open-sourced athttps://github.com/Sprinter1999/ROM.

AI is making mobile applications increasingly cooler, but also introduces serious privacy risks due to the extensive user data collection. Federated learning (FL), as a privacy-preserving machine learning paradigm, enables mobile devices to collaboratively learn a shared prediction model while keeping all training data on devices. However, a key obstacle towards practical cross-device FL training is the huge energy consumption, especially for lightweight mobile devices. Prior literature mostly optimizes the convergence speed and network communication cost. In this work, we first perform the experimental analysis of improving FL performance through low-precision training with energy-friendly Digital Signal Processor (DSP) on mobile devices. Then, we demonstrate that directly integrating the state-of-the-art INT8 (8-bit integer) training algorithm and classic FL protocols will significantly degrade the model accuracy. Finally, we propose a novel FL protocol, namelyQ-FedUpdate, incorporates two critical techniques: error-compensated aggregation and pipelined batch quantization. The former can ensure the tiny model updates be accumulated and take effects, and the latter can improve the DSP cache hit rate to reduce the context switching. Extensive experiments show that,Q-FedUpdatecan effectively reduce the on-device energy consumption by 21×, and accelerate the FL convergence by 6.1× with only 2% accuracy loss.

Federated learning (FL) has been widely adopted as a privacy-preserving model training paradigm. However, traditional FL protocol heavily relies on data transmission between clients and servers across the wide-area network (WAN), which is tightly constrained and unreliable, therefore causing expensive communication and slow convergence. To this end, we propose a LAN-aware FL (LanFL) protocol, which can efficiently leverage the network capacity of the local-area network (LAN). By frequent model aggregation among the devices within the same LAN, we can significantly reduce the global aggregation across WAN, thus accelerating the training process. However, due to the unique challenges introduced by LAN, it’s not easy to efficiently utilize LAN resources while preserving the original dignity of FL performance. Therefore, LanFL also incorporates several critical techniques: LAN-aware hierarchical aggregation, intraLAN device topology construction, and inter-LAN heterogeneous bandwidth coordination. Extensive real-world experiments are conducted and the experimental results show that LanFL can significantly accelerate FL training up to $6.0 \times$, while preserving the model accuracy.

In the current AI era, mobile devices such as smartphones are tasked with executing a myriad of deep neural networks (DNNs) locally. It presents a complex landscape, as these models are highly fragmented in terms of architecture, operators, and implementations. Such fragmentation poses significant challenges to the co-optimization of hardware, systems, and algorithms for efficient and scalable mobile AI.

AI is making the Web an even cooler place, but also introduces serious privacy risks due to the extensive user data collection. Federated learning (FL), as a privacy-preserving machine learning paradigm, enables mobile devices to collaboratively learn a shared prediction model while keeping all training data on devices. However, a key obstacle towards practical cross-device FL training is huge energy consumption, especially for lightweight mobile devices. In this work, we perform the first-of-its-kind analysis of improving FL performance through low-precision training with an energy-friendly Digital Signal Processor (DSP) on mobile devices. We first demonstrate that directly integrating the state-of-the-art INT8 (8-bit integer) training algorithm and classic FL protocols will significantly degrade the model accuracy. Moreover, we observe that there are still unavoidable frequent quantization operations on devices that cause extreme load stress on DSP-enabled INT8 training. To address the above challenges, we present Q-FedUpdate, an FL framework that efficiently preserves model accuracy with ultra-low energy consumption. It maintains a global full-precision model and allows the tiny model updates to be continuously accumulated, instead of being erased by the quantization. Furthermore, it introduces pipelining technology to parallel CPU-based quantization and DSP-enabled training, which reduces the floating-point computation overhead of frequent data quantization. Extensive experiments show that Q-FedUpdate can effectively reduce the on-device energy consumption by 21×, and accelerate the FL convergence by 6.1× with only 2% accuracy loss.

Large constellations of Low Earth Orbit (LEO) satellites have been launched for Earth observation and satellite-ground communication, which collect massive imagery and sensor data. These data can enhance the AI capabilities of satellites to address global challenges such as real-time disaster navigation and mitigation. Prior studies proposed leveraging federated learning (FL) across satellite-ground to collaboratively train a share machine learning (ML) model in a privacy-preserving mechanism. However, they mostly focus on single unique challenges such as limited ground-to-satellite bandwidth, short connection window, and long connection cycle, while ignoring the completeness of these challenges in deploying efficient FL frameworks in space. In this paper, we propose an efficient satellite-ground FL framework, SatelliteFL, to address these three challenges collectively. Its key idea is to ensure that each satellite must complete per-round training within each connection window. Moreover, we design a progressive block-wise quantization algorithm that determines a unique bitwidth for each block of the ML model to maximize the model utility while not exceeding the connection window. We evaluate SatelliteFL by plugging an implemented FL platform into real-world satellite networks and satellite images. The results show that SatelliteFL highly accelerates the convergence by up to 2.8× and improves the bandwidth utilization ratio by up to 9.3× compared to the state-of-the-art methods.

Differential privacy (DP) enables model training with a guaranteed bound on privacy leakage, therefore is widely adopted in federated learning (FL) to protect the model update. However, each DP-enhanced FL job accumulates privacy leakage, which necessitates a unified platform to enforce a global privacy budget for each dataset owned by users. In this work, we present a novel DP-enhanced FL platform that treats privacy as a resource and schedules multiple FL jobs across sensitive data. It first introduces a novel notion of device-time blocks for distributed data streams. Such data abstraction enables fine-grained privacy consumption composition across multiple FL jobs. Regarding the non-replenishable nature of the privacy resource (that differs it from traditional hardware resources like CPU and memory), it further employs an allocation-then-recycle scheduling algorithm. Its key idea is to first allocate an estimated upper-bound privacy budget for each arrived FL job, and then progressively recycle the unused budget as training goes on to serve further FL jobs. Extensive experiments show that our platform is able to deliver up to 2.1× as many completed jobs while reducing the violation rate by up to 55.2% under limited privacy budget constraint.

Federated learning (FL) has emerged as a prominent paradigm enabling collaborative model training without transmitting local data, thereby safeguarding data privacy. However, the practical implementation of FL systems on these devices faces a significant challenge: the heterogeneous corruption of data on individual clients, leading to unanticipated accuracy degradation during real-world deployment. In this work, we first introduce a realistic data corruption simulation framework to test the robustness of FL systems. In this framework, an in-depth analysis of potential data corruption patterns occurring on devices is conducted, followed by the construction of individual datasets with varying corruption types and degrees. Such data corruption results in the robustness degradation of conventional FL protocol (FedAVG) significantly higher than centralized learning (CL). Atop this key observation, we propose an adaptive FL protocol that emulates the CL training process. The protocol leverages imbalanced client data sampling to mitigate the negative impact of data corruption. Furthermore, a hybrid aggregation strategy is designed to accelerate model convergence and reduce additional communication overhead. Extensive experiments validate the effectiveness of our approach in enhancing the robustness of FL systems against client data corruption, which achieves up to 12% higher converge accuracy than FedAVG-based systems with acceptable overhead.

Abstract Short text classification has been a fundamental task in natural language processing, which benefits various applications, such as sentiment analysis, news tagging, and intent recommendation. However, classifying short texts is challenging due to the information sparsity in the text corpus. Besides, the performance of existing machine learning classification models largely relies on sufficient training data, yet labels can be scarce and expensive to obtain in real‐world text classification scenarios. In this article, we propose a novel self‐supervised short text classification method. Specifically, we first model the short text corpus as a heterogeneous graph to address the information sparsity problem. Then, we introduce a self‐attention‐based heterogeneous graph neural network model to learn short text embeddings. In addition, we adopt a self‐supervised learning framework to exploit internal and external similarities among short texts. Experiments on five real‐world short text benchmarks validate the effectiveness of our proposed method compared with the state‐of‐the‐art methods.

On-device learning is a promising technique for emerging privacy-preserving machine learning paradigms. However, through quantitative experiments, we find that commodity mobile devices cannot well support state-of-the-art DNN training with a large enough batch size, due to the limited local memory capacity. To fill the gap, we propose Melon, a memory-friendly on-device learning framework that enables the training tasks with large batch size beyond the physical memory capacity. Melon judiciously retrofits existing memory saving techniques to fit into resource-constrained mobile devices, i.e., recomputation and micro-batch. Melon further incorporates novel techniques to deal with the high memory fragmentation and memory adaptation. We implement and evaluate Melon with various typical DNN models on commodity mobile devices. The results show that Melon can achieve up to 4.33× larger batch size under the same memory budget. Given the same batch size, Melon achieves 1.89× on average (up to 4.01×) higher training throughput, and saves up to 49.43% energy compared to competitive alternatives. Furthermore, Melon reduces 78.59% computation on average in terms of memory budget adaptation.

Graph Neural Networks (GNNs) have achieved remarkable success in graph-related tasks by combining node features and graph topology elegantly. Most GNNs assume that the networks are homophilous, which is not always true in the real world, i.e., structure noise or disassortative graphs. Only a few works focus on generalizing graph neural networks to heterophilous or low homophilous networks, where connected nodes may have different labels. In this paper, we design a simple and effective Graph Structure Learning strategy based on Feature and Label consistency (GSLFL) to increase the homophilous level of networks for generalizing any existing GNNs to heterophilous networks. Specifically, we first introduce a method to learn graph structure based on node features and then modify the graph structure based on label consistency. Further, we combine the GSLFL with three existing GNNs to learn node representations and graph structure together. And we design a self-training method to iteratively train models and modify graph structure with pseudo-labels. Finally, our empirical results on 6 public networks with homophily or heterophily, and structure attacks show that our methods outperform the state-of-the-art methods in most cases.

Graph Neural Networks (GNNs) have achieved significant success in handling graph-structured data, such as knowledge graphs, citation networks, molecular structures, etc. However, most of them are usually shallow structures because of the over-smoothing problem that the representations of nodes are indistinguishable when stacking many layers. Several recent studies have tried to design deep GNNs for powerful expression ability by enlarging the receptive fields to aggregate information from high-order neighbors. But deep models may give rise to overfitting problem. In this paper, we propose a novel insight to aggregate more useful information based on multi-view which does not require deep structures. Specifically, we first design two complementary views to describe global topology and feature similarity of nodes. Then we devise an attention strategy to fuse node representations, named M ulti-V iew G raph C onvolutional N etowrk(MV-GCN). Further, we introduce a self-supervised technique to learn node representations by contrastive learning on different views, which can learn distinctive node embeddings from a large number of unlabeled data, named M ulti-V iew C ontrastive G raph C onvolutional Network(MV-CGC). Finally, we conduct extensive experiments on six public datasets for node classification, which prove the superiority of two proposed models compared with state-of-the-art methods.

Graph Neural Networks (GNNs) are powerful tools for modeling graph-structured data to solve the tasks such as node classification, link prediction along with graph classification. For the graph classification task, properly defining the pooling strategies to vary the size and structure of the input graph, is of vital importance to generate a graph-level representation of the input graph. However, the existing GNN models usually fail to effectively capture the graph substructure information in pooling process. Besides, the importance of nodes(supernodes) within a graph has not been well-reflected. To remedy these limitations, we propose Gated Structure Aware Pooling (GSAPool), a sparse and differentiable pooling method, which focuses on retaining the graph substructure information during the process of pooling in an end-to-end fashion. Specifically, GSAPool utilizes dual gates along with a self-attention network to integrate the local structure to form clusters' embeddings. It also employs a novel formulation to capture the importance of each node/supernode in an input graph. Experiment results show that GSAPool achieves competitive graph classification performance over the state-of-the-art graph representation learning methods.