Invariant Pretraining for Robust Code Representations

• URL: http://arxiv.org/abs/2608.15412v1
• Date: Sat, 15 Aug 2026 21:01:43 GMT
• Title: Invariant Pretraining for Robust Code Representations
• Abstract summary: Under invariant programs, semantically equivalent code written in different syntactic forms, learned representations degrade substantially.<n>We present an empirical study of this robustness gap across four encoder baselines, two downstream tasks, and four datasets.<n>Our method, invariant pretraining (InvPT), applies semantic-preserving transformations to the corpus.
• Score: 8.667720376952728
• License: http://creativecommons.org/publicdomain/zero/1.0/
• 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. Their robustness, however, is fragile: under invariant programs, semantically equivalent code written in different syntactic forms, learned representations degrade substantially even though program behavior is unchanged. We present an empirical study of this robustness gap across four encoder baselines, two downstream tasks, and four datasets, together with a minimal code-only continued pretraining recipe that closes much of it. Our method, invariant pretraining (InvPT), applies semantic-preserving transformations to the corpus and combines masked language modeling with multi-positive supervised contrastive learning that treats all augmentations of the same source function as positives, mixing self-contrast pairs (same code, different masks) with invariant-contrast pairs (transformed code) for positives of varying difficulty. Unlike prior contrastive code encoders, InvPT does not require paired natural-language data. Across our evaluation, InvPT improves robustness on transformed test sets by up to 11 percentage points on clone detection and 19 on code classification while matching or improving standard accuracy, and our ablations isolate multi-positive invariant contrast as the main source of the gains. Our aim is not a new objective but a careful measurement of where encoder robustness breaks and how far a simple, code-only recipe can recover it.

Related papers

• Type-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning [1.1386245013335434]
  Software clones are fragments of code that are similar or functionally equivalent to each other.<n>Detecting Type-IV clones, which are semantically equivalent but may differ syntactically, is difficult for traditional token- or syntax-based methods.<n>We propose LWVIC4Code, a non-contrastive representation learning approach specifically designed for Type-IV clone detection.
  arXiv  Detail & Related papers  (2026-09-15T15:42:06Z)
• Synthetic Semantic Supervision for Contrastive Code Representation Learning in Small Transformers: An Empirical Study [8.409799680956013]
  General-purpose code embeddings power tools for code search, classification, and retrieval.<n>We study an alternative: contrastive pretraining of small encoders with synthetically generated natural-language descriptions emphasizing code functionality and intent.
  arXiv  Detail & Related papers  (2026-09-03T11:41:09Z)
• Encoder-Decoder Manifold Alignment for Idempotent Generation [51.959208893243776]
  We argue that a key reason for this failure is a geometric mismatch between the manifold learned by the encoder and decoder.<n>We propose a new training framework that explicitly closes this gap by forcing the encoder and decoder to learn consistent representations of the same underlying data manifold.
  arXiv  Detail & Related papers  (2026-06-21T02:14:37Z)
• Readability-Robust Code Summarization via Meta Curriculum Learning [53.44612630063336]
  In the real world, code is often poorly structured or obfuscated, significantly degrading model performance.<n>We propose RoFTCodeSum, a novel fine-tuning method that enhances the robustness of code summarization against poorly readable code.
  arXiv  Detail & Related papers  (2026-01-09T02:38:24Z)
• Probing Pre-trained Language Models on Code Changes: Insights from ReDef, a High-Confidence Just-in-Time Defect Prediction Dataset [0.0]
  We present ReDef, a high-confidence benchmark of function-level modifications curated from 22 large-scale C/C++ projects.<n>Defective cases are anchored by revert commits, while clean cases are validated through post-hoc history checks.<n>This pipeline yields 3,164 defective and 10,268 clean modifications, offering substantially more reliable labels than prior existing resources.
  arXiv  Detail & Related papers  (2025-09-11T07:07:11Z)
• Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective [50.261681681643076]
  We propose a novel metric called SemVarEffect and a benchmark named SemVarBench to evaluate the causality between semantic variations in inputs and outputs in text-to-image synthesis.<n>Our work establishes an effective evaluation framework that advances the T2I synthesis community's exploration of human instruction understanding.
  arXiv  Detail & Related papers  (2024-10-14T08:45:35Z)
• Advanced Detection of Source Code Clones via an Ensemble of Unsupervised Similarity Measures [0.0]
  This research introduces a novel ensemble learning approach for code similarity assessment. The key idea is that the strengths of a diverse set of similarity measures can complement each other and mitigate individual weaknesses.
  arXiv  Detail & Related papers  (2024-05-03T13:42:49Z)
• Contrastive Test-Time Adaptation [83.73506803142693]
  We propose a novel way to leverage self-supervised contrastive learning to facilitate target feature learning. We produce pseudo labels online and refine them via soft voting among their nearest neighbors in the target feature space. Our method, AdaContrast, achieves state-of-the-art performance on major benchmarks.
  arXiv  Detail & Related papers  (2022-04-21T19:17:22Z)
• Disentangled Contrastive Learning for Learning Robust Textual Representations [13.880693856907037]
  We introduce the concept of momentum representation consistency to align features and leverage power normalization while conforming the uniformity. Our experimental results for the NLP benchmarks demonstrate that our approach can obtain better results compared with the baselines.
  arXiv  Detail & Related papers  (2021-04-11T03:32:49Z)
• Autoencoding Variational Autoencoder [56.05008520271406]
  We study the implications of this behaviour on the learned representations and also the consequences of fixing it by introducing a notion of self consistency. We show that encoders trained with our self-consistency approach lead to representations that are robust (insensitive) to perturbations in the input introduced by adversarial attacks.
  arXiv  Detail & Related papers  (2020-12-07T14:16:14Z)
• Contrastive Code Representation Learning [95.86686147053958]
  We show that the popular reconstruction-based BERT model is sensitive to source code edits, even when the edits preserve semantics. We propose ContraCode: a contrastive pre-training task that learns code functionality, not form.
  arXiv  Detail & Related papers  (2020-07-09T17:59:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.