-
On the Bottleneck of Graph Neural Networks and its Practical Implications
Uri Alon, Eran Yahav. poster
-
GraphCodeBERT: Pre-training Code Representations with Data Flow
Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie LIU, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, Michele Tufano, Shao Kun Deng, Colin Clement, Dawn Drain, Neel Sundaresan, Jian Yin, Daxin Jiang, Ming Zhou. poster
-
BUSTLE: Bottom-Up Program Synthesis Through Learning-Guided Exploration
Augustus Odena, Kensen Shi, David Bieber, Rishabh Singh, Charles Sutton, Hanjun Dai. spotlight
-
Retrieval-Augmented Generation for Code Summarization via Hybrid GNN
method for combining retrieval-based models and graph neural networks for source code summarization
Shangqing Liu, Yu Chen, Xiaofei Xie, Jing Kai Siow, Yang Liu. spotlight
-
Language-Agnostic Representation Learning of Source Code from Structure and Context
transforment \w seq + AST as input; utilizes several pairwise distance measures between AST nodes in the self-attention operation
Daniel Zügner, Tobias Kirschstein, Michele Catasta, Jure Leskovec, Stephan Günnemann. poster
-
Representing Partial Programs with Blended Abstract Semantics Maxwell Nye, Yewen Pu, Matthew Bowers, Jacob Andreas, Joshua B. Tenenbaum, Armando Solar-Lezama. poster
-
Generating Adversarial Computer Programs using Optimized Obfuscations
Shashank Srikant, Sijia Liu, Tamara Mitrovska, Shiyu Chang, Quanfu Fan, Gaoyuan Zhang, Una-May O'Reilly. poster
- GLUECode: A Benchmark for Source Code Machine Learning Models
- SpreadsheetCoder: Formula Prediction from Semi-structured Context
- Latent Programmer: Discrete Latent Codes for Program Synthesis
- Learning to Infer Run-Time Invariants from Source code
- GN-Transformer: Fusing AST and Source Code information in Graph Networks
- STRATA: Simple, Gradient-free Attacks for Models of Code
- Contrastive Code Representation Learning
- MISIM: A Novel Code Similarity System