Federated learning (FL) has emerged as a widely adopted paradigm for enabling edge learning with distributed data while ensuring data privacy. However, the traditional FL with deep neural networks trained via backpropagation can hardly meet the low-latency learning requirements in the sixth generation (6G) mobile networks. This challenge mainly arises from the high-dimensional model parameters to be transmitted and the numerous rounds of communication required for convergence due to the inherent randomness of the training process. To address this issue, we adopt the state-of-the-art principle of maximal coding rate reduction to learn linear discriminative features and extend the resultant white-box neural network into FL, yielding the novel framework of Low-Latency Federated Learning (LoLaFL) via forward-only propagation. LoLaFL enables layer-wise transmissions and aggregation with significantly fewer communication rounds, thereby considerably reducing latency. Additionally, we propose twononlinearaggregation schemes for LoLaFL. The first scheme is based on the proof that the optimal NN parameter aggregation in LoLaFL should be harmonic-mean-like. The second scheme further exploits the low-rank structures of the features and transmits the low-rank-approximated covariance matrices of features to achieve additional latency reduction. Theoretic analysis and experiments are conducted to evaluate the performance of LoLaFL. In comparison with traditional FL, the two nonlinear aggregation schemes for LoLaFL can achieve reductions in latency of over 87% and 97%, respectively, while maintaining comparable accuracies.

Third-party libraries (TPLs) play a critical role in modern software development by providing reusable code that accelerates project development. However, the vast number of TPLs available makes selecting the appropriate library for a given task or finding replacements for deprecated libraries a challenging task. Existing methods are limited, relying only on miningbased approaches or feature-based solutions. In this study, we propose an innovative attributed multiplex learning approach that combines both textual and relational data across multiple layers to perform effective analogical library recommendation and retrieval. By representing libraries as nodes with attributes and modeling cross-library relationships as graph edges, our method constructs an attributed multiplex network for TPL representation embeddings. Our approach uses a unified, concise model to include different aspects of information. The proposed inductive model can also address cold-start issues. Moreover, our model is scalable and can adapt to a large number of libraries. To validate our approach, we conduct experiments including an ablation study within the NPM ecosystem. By using a ground-truth data set of 8,308 libraries, the results demonstrate a recommendation precision of 89.8 % at Hit@10. Additionally, we contribute a new data set extracted from deprecation messages containing 4,070 migration rules, enriching the relatively small existing data sets in the NPM ecosystem. In summary, our approach is efficient and promising for supporting real-world, large-scale TPL recommendation and retrieval.

This work presents four novel entropy-based indices for measuring the community evolution of developer social networks (DSNs) in open source software (OSS) projects. The proposed indices offer a quantitative measure of community split, shrink, merge, and expand events. The indices have proven properties like monotonicity, and they have defined maximum and minimum values that signify meaningful scenarios. These indices can be combined to describe complex community evolution events such as emergence and extinction. Expanding upon these indices, this research proposes a novel machine learning approach, leveraging shapelet mining, to unearth representative patterns of community evolution. The results from real-world OSS projects show that these indices effectively capture various community evolution behaviors with a 94.1% accuracy compared to existing work. They also predict OSS team productivity with a 0.718 accuracy. With the shapelet mining and learning framework, the indices can identify patterns of community evolution and predict the survival of OSS projects with 93% accuracy 3 months before the projects’ last observed commits. The findings highlight the potential of these entropy-based indices for understanding OSS project status and predicting future trends, which are valuable for supporting future research on DSNs and OSS communities.

On open source software (OSS) platforms such as GitHub, forking and accepting pull-requests is an important approach for OSS projects to receive contributions, especially from external contributors who cannot directly commit into the source repositories. Having a large number of forks is often considered as an indicator of a project being popular. While extensive studies have been conducted to understand the reasons of forking, communications between forks, features and impacts of forks, there are few quantitative measures that can provide a simple yet informative way to gain insights about an OSS project's forks besides their count. Inspired by studies on biodiversity and OSS team diversity, in this paper, we propose an approach to measure the diversity of an OSS project's forks (i.e., its fork population). We devise a novel fork entropy metric based on Rao's quadratic entropy to measure such diversity according to the forks' modifications to project files. With properties including symmetry, continuity, and monotonicity, the proposed fork entropy metric is effective in quantifying the diversity of a project's fork population. To further examine the usefulness of the proposed metric, we conduct empirical studies with data retrieved from fifty projects on GitHub. We observe significant correlations between a project's fork entropy and different outcome variables including the project's external productivity measured by the number of external contributors' commits, acceptance rate of external contributors' pull-requests, and the number of reported bugs. We also observe significant interactions between fork entropy and other factors such as the number of forks. The results suggest that fork entropy effectively enriches our understanding of OSS projects' forks beyond the simple number of forks, and can potentially support further research and applications.

Understanding the evolution of communities in developer social networks (DSNs) around open source software (OSS) projects can provide valuable insights about the socio-technical process of OSS development. Existing studies show the evolutionary behaviors of social communities can effectively be described using patterns including split, shrink, merge, expand, emerge, and extinct. However, existing pattern-based approaches are limited in supporting quantitative analysis, and are potentially problematic for using the patterns in a mutually exclusive manner when describing community evolution. In this work, we propose that different patterns can occur simultaneously between every pair of communities during the evolution, just in different degrees. Four entropy-based indices are devised to measure the degree of community split, shrink, merge, and expand, respectively, which can provide a comprehensive and quantitative measure of community evolution in DSNs. The indices have properties desirable to quantify community evolution including monotonicity, and bounded maximum and minimum values that correspond to meaningful cases. They can also be combined to describe more patterns such as community emerge and extinct. We conduct studies with real-world OSS projects to evaluate the validity of the proposed indices. The results suggest the proposed indices can effectively capture community evolution, and are consistent with existing approaches in detecting evolution patterns in DSNs with an accuracy of 94.1%. The results also show that the indices are useful in predicting OSS team productivity with an accuracy of 0.718. In summary, the proposed approach is among the first to quantify the degree of community evolution with respect to different patterns, which is promising in supporting future research and applications about DSNs and OSS development.