← Back to all news
arXiv Machine Learning By Luciano Marchezan, Kevin Delcourt, Eugene Syriani, Houari Sahraoui

Type-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning

Read the original on arXiv Machine Learning →

The paper introduces LWVIC4Code, a non‑contrastive, layer‑wise representation learning method for detecting Type‑IV code clones—semantically equivalent fragments that differ syntactically. It builds on the VICReg framework, adding cross‑layer consistency regularization and depth‑dependent weighting to refine semantic information across transformer layers. Experiments on Python and multi‑language datasets show that LWVIC4Code matches or outperforms contrastive baselines and zero‑shot large language models, generalizing well to Java and C# without requiring negative samples.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Aug 18

Invariant Pretraining for Robust Code Representations

arXiv:2608. 15412v1 Announce Type: cross Abstract: Encoder-based code representation models remain widely deployed for discriminative tasks such as clone detection and code classification, where their small size and low inference cost are decisive.

By Yifeng He, Yundi Xu, Christopher Castro Gaw Gonzalo, Zili Wang, Hao Chen
More like this →
arXiv AI
Sep 4

Synthetic Semantic Supervision for Contrastive Code Representation Learning in Small Transformers: An Empirical Study

The paper investigates using synthetic natural-language descriptions to contrastively pretrain small transformer encoders for code representation. By pairing generated descriptions with code in a dual-encoder setup during training and discarding them at inference, the authors achieve significant improvements over traditional pretraining baselines on most evaluated tasks. When fine‑tuned, these models match or surpass much larger zero‑shot models and remain competitive with execution‑aware supervision, indicating a scalable alternative for code embeddings.

By Kenneth Paulsen, Florian Tambon, Mike Papadakis, Shin Yoo
llmsragfine-tuningbenchmarks
More like this →
arXiv AI
Aug 19

LSem2Vec: A Simple yet Effective Two-Stage Approach for Source Code Embedding

The paper introduces LSem2Vec, a two‑stage method that first uses a large language model to extract source code semantics and then applies a sentence embedding model to produce vector representations. This approach removes the need for task‑specific training or fine‑tuning, addressing errors in LLM outputs. Experiments on three datasets across multiple programming languages show that LSem2Vec outperforms five state‑of‑the‑art unsupervised methods.

By Zixiang Xian, Chenhui Cui, Rubing Huang, Chunrong Fang, Zhenyu Chen
llmsragfine-tuningbenchmarks
More like this →