Xinqiang Xie

Software developer recommendation is a critical task for online collaboration platforms. Identifying suitable developers remains challenging due to difficulties in capturing interaction behavioral preferences and semantic relevance, as well as handling data sparsity and cold-start issues. Traditional approaches typically model developers’ competencies (e.g., skills, expertise, and experience) or infer their preferences from historical task interactions. However, they often underperform because they fail to address several key challenges: (1) effectively capturing deep interaction behavioral preferences; (2) modeling latent textual semantics between developers and tasks; and (3) integrating behavioral preferences with semantic relevance in a unified manner. To address these challenges, we propose HiSDevRec, a novel dual-modality hybrid framework for developer recommendation that jointly models interaction-based behavioral preferences and textual semantic relevance. Specifically, we introduce a hybrid representation learning approach that integrates ID-based behavioral patterns with semantic representations derived from textual information. We further employ graph attention networks to capture higher-order propagation over the interaction graph, generating enriched representations for developers and tasks. In addition, we design a self-supervised disentanglement mechanism to explicitly separate behavioral and semantic representations, improving recommendation performance while enabling factor-level interpretability. Finally, we conduct extensive experiments on two real-world datasets, along with a case study and a user survey in an industrial setting. The results demonstrate that HiSDevRec consistently outperforms state-of-the-art baselines.

Background: Accurate prediction of ICU mortality based on physiological data can significantly facilitate timely interventions and improve patient outcomes. However, patient heterogeneity, including variations in age, disease types, and regional differences, along with the dynamic nature of ICU data, leads to significant limitations in the generalization ability and self-updating capability of existing prediction models. Therefore, developing dynamically adaptive predictive methods is crucial to ensure model adaptability and reliability in real-world clinical settings. Methods: We propose AdaICU, a novel framework that integrates unsupervised domain adaptation and incremental learning for cross-ICU mortality prediction. The framework first aligns feature distributions between source and target domains using domain-adversarial training, and subsequently updates the model through incremental learning as new target-domain data become available. Results: Extensive experiments on the PhysioNet 2012 dataset show that AdaICU consistently outperforms baseline models across multiple cross-domain settings. In particular, AdaICU achieves AUROC improvements of approximately 2–6% over the strongest baseline across different transfer tasks. Substantial improvements are also observed in AUPRC, indicating enhanced capability in identifying high-risk patients. In addition, AdaICU improves accuracy by approximately 4–8% and achieves higher positive predictive value, suggesting more reliable positive predictions. Overall, these results highlight the effectiveness of the proposed framework in addressing cross-domain distribution shifts. Conclusion: By jointly addressing cross-domain distribution shifts and post-deployment model adaptation, AdaICU provides a practical and effective framework for ICU mortality prediction in settings with limited labeled data. This capability makes it particularly promising for real-world application in dynamic clinical environments with evolving data distributions.

Collaboration efficiency is of paramount importance for software development. Finding suitable developers is critical and challenging due to the difficulty of capturing developers' expertises, relevance as well as the sparsity of explicit developer-task interactions. To tackle this problem, existing developer recommendation approaches focus on modelling the developer's expertise or interactions with tasks based on their historical information. However, such approaches often suffer from low performance because they ignore some useful information that might help improve recommendation performance, such as 1) developers' collaboration relationship; 2) the interaction relationship between developer and task; and 3) the tasks' similarity relationship. To leverage the above-mentioned relationships, this paper proposes DevRec, a novel multi-relationship embedded approach for software developer recommendation. We first formally define the multi-relationships and then learn the vector representations (aka. embeddings) of developers and tasks. Second, we explicitly encoded the multi-relationships into the embedding process. Third, to refine the embeddings of developers and tasks, we recursively propagate the embeddings from their high-order connectivity based on graph convolution network. Moreover, to reveal the importance of different relationships, we generate their attentive weights based on attention mechanism. Finally, to evaluate the performance of DevRec, we conduct extensive experiments on two real-world datasets, and to investigate the usefulness of DevRec in practice, we conduct a user study at a large software company. The results show that DevRec outperforms other five state-of-the-art approaches significantly.