English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep Learning (DL) models to analyze source code have shown immense promiseduring the past few years. More recently, self-supervised pre-training hasgained traction for learning generic code representations valuable for manydownstream SE tasks, such as clone and bug detection.  While previous work successfully learned from different code abstractions(e.g., token, AST, graph), we argue that it is also essential to factor in howdevelopers code day-to-day for general-purpose representation learning. On theone hand, human developers tend to write repetitive programs referencingexisting code snippets from the current codebase or online resources (e.g.,Stack Overflow website) rather than implementing functions from scratch; suchbehaviors result in a vast number of code clones. In contrast, a deviant cloneby mistake might trigger malicious program behaviors.  Thus, as a proxy to incorporate developers' coding behavior into thepre-training scheme, we propose to include code clones and their deviants. Inparticular, we propose CONCORD, a self-supervised, contrastive learningstrategy to place benign clones closer in the representation space while movingdeviants further apart. We show that CONCORD's clone-aware contrastive learningdrastically reduces the need for expensive pre-training resources whileimproving the performance of downstream SE tasks. We also empiricallydemonstrate that CONCORD can improve existing pre-trained models to learnbetter representations that consequently become more efficient in bothidentifying semantically equivalent programs and differentiating buggy fromnon-buggy code.

CONCORD: Clone-aware Contrastive Learning for Source Code