Personalized Federated Learning (PFL) aims to provide client-specific models that adapt to local data distributions while leveraging shared knowledge across clients. A common design in PFL is the head-representation architecture, which combines a shared global representation with a local head on each client. Although effective, deploying this architecture in real-world systems remains challenging due to the presence of stragglers and the high communication cost. To address these issues, we propose FedSTEP, a unified framework that integrates asynchronous training with dynamic communication sparsification. Specifically, it adaptively adjusts each client's local training duration and communication sparsity based on staleness, enabling more efficient coordination between local adaptation and global representation. This design mitigates the impact of stragglers and ensures robust performance in heterogeneous environments. We provide a theoretical analysis of the convergence behavior and communication efficiency of FedSTEP under standard assumptions. Extensive experiments on five public datasets demonstrate that FedSTEP consistently outperforms existing methods. It achieves up to 4.65% higher accuracy, a 3.68× speedup in training, and a 1.91× reduction in communication cost.

Large pre-trained models have significantly advanced computer vision (CV) and natural language processing (NLP). However, their deployment is challenging in privacy-sensitive scenarios where data must remain decentralized. Federated Learning (FL) addresses this issue by enabling local model training without sharing raw data. Despite this advantage, integrating large models into FL introduces challenges such as training inefficiencies, label scarcity, and data heterogeneity. In this paper, we propose FedDiAL, a framework designed to effectively incorporate large pre-trained models into FL while addressing these challenges. At its core, FedDiAL, features the novel HDis-Net, which enhances the efficiency of large models in resource-constrained environments. We introduce a two-phase training strategy with probabilistic feature augmentation to improve feature discrimination. Additionally, we propose an adaptive pseudo-labeling method to generate high-confidence labels, mitigating label scarcity. To handle data heterogeneity, we develop a focused fine-tuning strategy that adapts HDis-Net to diverse client data distributions. Our theoretical analysis establishes the convergence of HDis-Net. Extensive experiments on four datasets, including Tiny ImageNet and AG News, demonstrate that FedDiAL outperforms state-of-the-art methods, achieving up to a 35.66% accuracy improvement in both CV and NLP tasks.

The rapid decline in groundwater around the world poses a significant challenge to sustainable agriculture. To address this issue, agricultural managed aquifer recharge (Ag-MAR) is proposed to recharge the aquifer by artificially flooding agricultural lands using surface water. Ag-MAR requires a carefully selected flooding schedule to avoid affecting the oxygen absorption of crop roots. However, current Ag-MAR scheduling does not take into account complex environmental factors such as weather and soil oxygen, resulting in crop damage and insufficient recharging amounts. This paper proposes MARLP, the first end-to-end data-driven control system for Ag-MAR. We first formulate Ag-MAR as an optimization problem. To that end, we analyze four-year in-field datasets, which reveal the multi-periodicity feature of the soil oxygen level trends and the opportunity to use external weather forecasts and flooding proposals as exogenous clues for soil oxygen prediction. Then, we design a two-stage forecasting framework. In the first stage, it extracts both the cross-variate dependency and the periodic patterns from historical data to conduct preliminary forecasting. In the second stage, it uses weather-soil and flooding-soil causality to facilitate an accurate prediction of soil oxygen levels. Finally, we conduct model predictive control (MPC) for Ag-MAR flooding. To address the challenge of large action spaces, we devise a heuristic planning module to reduce the number of flooding proposals to enable the search for optimal solutions. Real-world experiments show that MARLP reduces the oxygen deficit ratio by 86.8% while improving the recharging amount in unit time by 35.8%, compared with the previous four years.

This paper presents a novel map matching framework that adopts deep learning techniques to map a sequence of cell tower locations to a trajectory on a road network. Map matching is an essential pre-processing step for many applications, such as traffic optimization and human mobility analysis. However, most recent approaches are based on hidden Markov models (HMMs) or neural networks that are hard to consider high-order location information or heuristics observed from real driving scenarios. In this paper, we develop a deep reinforcement learning based map matching framework for cellular data, named as DMM, which adopts a recurrent neural network (RNN) coupled with a reinforcement learning scheme to identify the most-likely trajectory of roads given a sequence of cell towers. To transform DMM into a practical system, several challenges are addressed by developing a set of techniques, including spatial-aware representation of input cell tower sequences, an encoder-decoder based RNN network for map matching model with variable-length input and output, and a global heuristics-driven reinforcement learning based scheme for optimizing the parameters of the encoder-decoder map matching model. Extensive experiments on a large-scale anonymized cellular dataset reveal that DMM provides high map matching accuracy and fast inference time.

In this paper, we propose a single-agent Monte Carlo based reinforced feature selection (MCRFS) method, as well as two efficiency improvement strategies, i.e., early stopping (ES) strategy and reward-level interactive (RI) strategy. Feature selection is one of the most important technologies in data prepossessing, aiming to find the optimal feature subset for a given downstream machine learning task. Enormous research has been done to improve its effectiveness and efficiency. Recently, the multi-agent reinforced feature selection (MARFS) has achieved great success in improving the performance of feature selection. However, MARFS suffers from the heavy burden of computational cost, which greatly limits its application in real-world scenarios. In this paper, we propose an efficient reinforcement feature selection method, which uses one agent to traverse the whole feature set, and decides to select or not select each feature one by one. Specifically, we first develop one behavior policy and use it to traverse the feature set and generate training data. And then, we evaluate the target policy based on the training data and improve the target policy by Bellman equation. Besides, we conduct the importance sampling in an incremental way, and propose an early stopping strategy to improve the training efficiency by the removal of skew data. In the early stopping strategy, the behavior policy stops traversing with a probability inversely proportional to the importance sampling weight. In addition, we propose a reward-level interactive strategy to improve the training efficiency via reward-level external advice. Finally, we design extensive experiments on real-world data to demonstrate the superiority of the proposed method.