Výsledky vyhledávání

Report

Zero-Shot Code Representation Learning via Prompt Tuning

Autor: Cui, Nan, Gu, Xiaodong, Shen, Beijun

Learning code representations has been the core prerequisite of many software engineering tasks such as code clone detection and code generation. State-of-the-art program representation techniques mainly utilize pre-trained language models (PLMs) suc

Externí odkaz: http://arxiv.org/abs/2404.08947

Zobrazit plný text záznamu

Report

Equipping Federated Graph Neural Networks with Structure-aware Group Fairness

Autor: Cui, Nan, Wang, Xiuling, Wang, Wendy Hui, Chen, Violet, Ning, Yue

Graph Neural Networks (GNNs) have been widely used for various types of graph data processing and analytical tasks in different domains. Training GNNs over centralized graph data can be infeasible due to privacy concerns and regulatory restrictions.

Externí odkaz: http://arxiv.org/abs/2310.12350

Zobrazit plný text záznamu

Report

Zero-Shot Program Representation Learning

Autor: Cui, Nan, Jiang, Yuze, Gu, Xiaodong, Shen, Beijun

Learning program representations has been the core prerequisite of code intelligent tasks such as code search and code clone detection. The state-of-the-art pre-trained models such as CodeBERT require the availability of large-scale code corpora. How

Externí odkaz: http://arxiv.org/abs/2204.08360

Zobrazit plný text záznamu