arXiv subjects

Chengjie Ma

Publications and source records attributed to Chengjie Ma.

5 recordsLinked to original sources

arXiv2025

Breaking the Capacity Bottleneck in Model-Heterogeneous Federated Learning via Gradual Model Restoration

Federated learning (FL) enables distributed model training, yet in heterogeneous deployments, Bandwidth-Constrained Clients (BCCs) often contribute inefficiently due to limited uplink bandwidth. In model-heterogeneous FL with fixed small sub-models, BCCs with sub-models may improve quickly in early rounds but become under-parameterized later, resulting in slow convergence and poor generalization. To address this challenge, we propose FedGMR, a federated learning framework centered around Gradual Model Restoration (GMR), where GMR progressively increases each client's sub-model density during training, allowing BCCs to remain effective contributors throughout optimization. To make GMR practical under real-world heterogeneity, FedGMR is realized as an end-to-end workflow with asynchronous coordination and stable, mask-aware aggregation. We further establish convergence guarantees, showing that the aggregation error scales with the average sub-model density across clients and rounds, and that GMR provably narrows the gap toward full-model FL. Extensive experiments on FEMNIST, CIFAR-10, ImageNet-100, and StackOverflow demonstrate that FedGMR improves both convergence speed and final accuracy, especially under severe heterogeneity and non-IID data distributions. Code is available at https://github.com/machengjie321/ICML2026-FedGMR.

cs.DC↗

arXiv2024

Federated Learning based on Pruning and Recovery

A novel federated learning training framework for heterogeneous environments is presented, taking into account the diverse network speeds of clients in realistic settings. This framework integrates asynchronous learning algorithms and pruning techniques, effectively addressing the inefficiencies of traditional federated learning algorithms in scenarios involving heterogeneous devices, as well as tackling the staleness issue and inadequate training of certain clients in asynchronous algorithms. Through the incremental restoration of model size during training, the framework expedites model training while preserving model accuracy. Furthermore, enhancements to the federated learning aggregation process are introduced, incorporating a buffering mechanism to enable asynchronous federated learning to operate akin to synchronous learning. Additionally, optimizations in the process of the server transmitting the global model to clients reduce communication overhead. Our experiments across various datasets demonstrate that: (i) significant reductions in training time and improvements in convergence accuracy are achieved compared to conventional asynchronous FL and HeteroFL; (ii) the advantages of our approach are more pronounced in scenarios with heterogeneous clients and non-IID client data.

cs.LG↗

arXiv2023

Topic model based on co-occurrence word networks for unbalanced short text datasets

We propose a straightforward solution for detecting scarce topics in unbalanced short-text datasets. Our approach, named CWUTM (Topic model based on co-occurrence word networks for unbalanced short text datasets), addresses the challenge of sparse and unbalanced short text topics by mitigating the effects of incidental word co-occurrence. This allows our model to prioritize the identification of scarce topics (low-frequency topics). Unlike previous methods, CWUTM leverages co-occurrence word networks to capture the topic distribution of each word, and enhances the sensitivity in identifying scarce topics by redefining the calculation of node activity and normalizing the representation of both scarce and abundant topics to some extent. Moreover, CWUTM adopts Gibbs sampling, similar to LDA, making it easily adaptable to various application scenarios. Extensive experimental validation on unbalanced short-text datasets demonstrates the superiority of CWUTM compared to baseline approaches in discovering scarce topics. According to the experimental results, the proposed model is effective in early and accurate detection of emerging topics or unexpected events on social platforms.

cs.CL↗

arXiv2023

Federated Topic Model and Model Pruning Based on Variational Autoencoder

Topic modeling has emerged as a valuable tool for discovering patterns and topics within large collections of documents. However, when cross-analysis involves multiple parties, data privacy becomes a critical concern. Federated topic modeling has been developed to address this issue, allowing multiple parties to jointly train models while protecting privacy. However, there are communication and performance challenges in the federated scenario. To solve these problems, this paper proposes a method to establish a federated topic model while ensuring the privacy of each node and uses neural network model pruning to accelerate the model. The client periodically sends cumulative neuron gradients and model weights to the server, and the server prunes the model. To address different requirements, two methods are proposed to determine the pruning rate. The first slowly prunes throughout training, which has limited acceleration during training but can ensure higher accuracy and significantly reduce inference time. The second quickly reaches the target pruning rate early in training and then continues training with a smaller model. This approach may lose more useful information but can complete training faster. Experimental results show that the proposed variational-autoencoder-based federated topic model pruning can greatly accelerate training while maintaining model performance.

cs.LG↗

arXiv2022

A Rare Topic Discovery Model for Short Texts Based on Co-occurrence word Network

We provide a simple and general solution for the discovery of scarce topics in unbalanced short-text datasets, namely, a word co-occurrence network-based model CWIBTD, which can simultaneously address the sparsity and unbalance of short-text topics and attenuate the effect of occasional pairwise occurrences of words, allowing the model to focus more on the discovery of scarce topics. Unlike previous approaches, CWIBTD uses co-occurrence word networks to model the topic distribution of each word, which improves the semantic density of the data space and ensures its sensitivity in identify-ing rare topics by improving the way node activity is calculated and normal-izing scarce topics and large topics to some extent. In addition, using the same Gibbs sampling as LDA makes CWIBTD easy to be extended to vari-ous application scenarios. Extensive experimental validation in the unbal-anced short text dataset confirms the superiority of CWIBTD over the base-line approach in discovering rare topics. Our model can be used for early and accurate discovery of emerging topics or unexpected events on social platforms.

cs.IR↗