facebookresearch / mmd
ML models often mispredict, and it is hard to tell when and why. We present a data mining based approach to discover whether there is a certain form of data that particular causes the model to mispredict.
☆18Updated 2 years ago
Related projects: ⓘ
- [ICLR 2021] "Generating Adversarial Computer Programs using Optimized Obfuscations" by Shashank Srikant, Sijia Liu, Tamara Mitrovska, Shi…☆25Updated 2 years ago
- The dataset for the variable-misuse task, used in the ICLR 2020 paper 'Global Relational Models of Source Code' [https://openreview.net/f…☆22Updated 4 years ago
- VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning☆38Updated last year
- Source Code Data Augmentation for Deep Learning: A Survey.☆58Updated 3 months ago
- [EMNLP'22] Code for 'Exploring Representation-level Augmentation for Code Search'☆26Updated 11 months ago
- ☆19Updated last year
- Code for the AAAI 2023 paper "CodeAttack: Code-based Adversarial Attacks for Pre-Trained Programming Language Models☆22Updated last year
- ☆10Updated last year
- ☆42Updated last year
- MODIT: On Multi-Modal Learning of Editing Source Code.☆19Updated 3 years ago
- Official code of our work, AVATAR: A Parallel Corpus for Java-Python Program Translation.☆53Updated last month
- Releasing code for "ReCode: Robustness Evaluation of Code Generation Models"☆46Updated 5 months ago
- ☆15Updated 2 years ago
- Code Snippet Recommendation from Stack Overflow Post☆17Updated 3 years ago
- Data and Code for Reproducing "Global Relational Models of Source Code"☆82Updated 3 years ago
- Mining tool and large-scale datasets of single statement bug fixes in Python☆14Updated 9 months ago
- ☆11Updated 6 months ago
- ManyTypes4Py: A benchmark Python dataset for machine learning-based type inference☆18Updated 2 years ago
- ☆13Updated 5 months ago
- ☆28Updated last year
- A benchmark for evaluating embeddings of identifiers in source code.☆22Updated 3 years ago
- Generating Adversarial Examples for Holding Robustness of Source Code Processing Models☆12Updated 2 years ago
- Code implementation for CoTexT: Multi-task Learning with Code-Text Transformer☆35Updated 3 years ago
- code and data for paper "ComFormer: Code Comment Generation via Transformer and Fusion Method-based Hybrid Code Representation" accepted …☆14Updated 2 years ago
- C# Data Extraction for "Learning to Represent Edits"☆27Updated 5 years ago
- JEMMA: An Extensible Java dataset for Many ML4Code Applications☆19Updated last year
- ☆38Updated last year
- ESEC/FSE'21: Prediction-Preserving Program Simplification☆10Updated last year
- This is the artifact for paper “Are Machine Learning Cloud APIs Used Correctly? (#421)” in ICSE2021☆15Updated 3 years ago
- Code for "Deep Graph Matching and Searching for Semantic Code Retrieval"☆24Updated 2 years ago