paper-with-me

홈 › Papers

On the Generalizability of Neural Program Models with respect to Semantic-Preserving Program Transformations

2020-07-31 · Md Rafiqul Islam Rabin, Nghi D. Q. Bui, Ke Wang, Yijun Yu, Lingxiao Jiang, Mohammad Amin Alipour

With the prevalence of publicly available source code repositories to train deep neural network models, neural program models can do well in source code analysis tasks such as predicting method names in given programs that cannot be easily done by traditional program analysis techniques. Although such neural program models have been tested on various existing datasets, the extent to which they generalize to unforeseen source code is largely unknown. Since it is very challenging to test neural program models on all unforeseen programs, in this paper, we propose to evaluate the generalizability of neural program models with respect to semantic-preserving transformations: a generalizable neural program model should perform equally well on programs that are of the same semantics but of different lexical appearances and syntactical structures. We compare the results of various neural program models for the method name prediction task on programs before and after automated semantic-preserving transformations. We use three Java datasets of different sizes and three state-of-the-art neural network models for code, namely code2vec, code2seq, and GGNN, to build nine such neural program models for evaluation. Our results show that even with small semantically preserving changes to the programs, these neural program models often fail to generalize their performance. Our results also suggest that neural program models based on data and control dependencies in programs generalize better than neural program models based only on abstract syntax trees. On the positive side, we observe that as the size of the training dataset grows and diversifies the generalizability of correct predictions produced by the neural program models can be improved too. Our results on the generalizability of neural program models provide insights to measure their limitations and provide a stepping stone for their improvement.

📄 PDF Abstract BibTeX arXiv:2008.01566

Code (1)

mdrafiqulrabin/tnpa-generalizability 공식 구현

Tasks

Method name prediction

Methods 이 논문이 사용한 방법론

GGS-NNs 설명 없음

Similar Papers 제목 키워드 기반

Evaluation of Generalizability of Neural Program Analyzers under Semantic-Preserving Transformations

2020-04-15 · Md Rafiqul Islam Rabin, Mohammad Amin Alipour

The abundance of publicly available source code repositories, in conjunction with the advances in neural networks, has enabled data-driven approaches to program analysis. These approaches, called neural program analyzers…

Method name prediction

Evaluating the Generalizability of LLMs in Automated Program Repair

2025-03-12 · Fengjie Li, Jiajun Jiang, Jiajun Sun, Hongyu Zhang

LLM-based automated program repair methods have attracted significant attention for their state-of-the-art performance. However, they were primarily evaluated on a few well known datasets like Defects4J, raising question…

Program RepairPrompt Engineering

GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis

2022-05-27 · Yushi Cao, Zhiming Li, Tianpei Yang, Hao Zhang 외

Despite achieving superior performance in human-level control problems, unlike humans, deep reinforcement learning (DRL) lacks high-order intelligence (e.g., logic deduction and reuse), thus it behaves ineffectively than…

Decision MakingDeep Reinforcement LearningProgram Synthesisreinforcement-learning+2

Making Neural Programming Architectures Generalize via Recursion

2017-04-21 · Jonathon Cai, Richard Shin, Dawn Song

Empirically, neural networks that attempt to learn programs from data have exhibited poor generalizability. Moreover, it has traditionally been difficult to reason about the behavior of these models beyond a certain leve…

On the Relation between Weak Completion Semantics and Answer Set Semantics

2019-10-16 · Emmanuelle-Anna Dietz Saldanha, Jorge Fandinno

The Weak Completion Semantics (WCS) is a computational cognitive theory that has shown to be successful in modeling episodes of human reasoning. As the WCS is a recently developed logic programming approach, this paper i…

RelationTranslation