# Data-Driven AI Model Signal-Awareness Enhancement and Introspection

arXiv: https://arxiv.org/abs/2111.05827 · HTML: https://mlsanity.com/paper/2111.05827/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 52 references that are in the map.
- First posted on arXiv 10 Nov 2021.

## Builds on (most cited first, 25 of 25)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks](https://mlsanity.com/paper/1909.03496/) (2019)
- [Towards Stable and Efficient Training of Verifiably Robust Neural Networks](https://mlsanity.com/paper/1906.06316/) (2019)
- [Automated Vulnerability Detection in Source Code Using Deep Representation Learning](https://mlsanity.com/paper/1807.04320/) (2018)
- [An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation](https://mlsanity.com/paper/1812.08693/) (2018)
- [DeepBugs: A Learning Approach to Name-based Bug Detection](https://mlsanity.com/paper/1805.11683/) (2018)
- [Multi-task Learning based Pre-trained Language Model for Code Completion](https://mlsanity.com/paper/2012.14631/) (2020)
- [On Learning Meaningful Code Changes via Neural Machine Translation](https://mlsanity.com/paper/1901.09102/) (2019)
- [D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis](https://mlsanity.com/paper/2102.07995/) (2021)
- [Learning to Update Natural Language Comments Based on Code Changes](https://mlsanity.com/paper/2004.12169/) (2020)
- [Understanding Neural Code Intelligence Through Program Simplification](https://mlsanity.com/paper/2106.03353/) (2021)
- [Probing Model Signal-Awareness via Prediction-Preserving Input Minimization](https://mlsanity.com/paper/2011.14934/) (2020)
- [Learning How to Mutate Source Code from Bug-Fixes](https://mlsanity.com/paper/1812.10772/) (2018)
- [Learning to map source code to software vulnerability using code-as-a-graph](https://mlsanity.com/paper/2006.08614/) (2020)
- [Shallow or Deep? An Empirical Study on Detecting Vulnerabilities using Deep Learning](https://mlsanity.com/paper/2103.11940/) (2021)
- [Towards security defect prediction with AI](https://mlsanity.com/paper/1808.09897/) (2018)

## Built on by (most cited first, 1 of 1)

- [Study of Distractors in Neural Models of Code](https://mlsanity.com/paper/2303.01739/) (2023)

## Abstract (arXiv)

AI modeling for source code understanding tasks has been making significant progress, and is being adopted in production development pipelines. However, reliability concerns, especially whether the models are actually learning task-related aspects of source code, are being raised. While recent model-probing approaches have observed a lack of signal awareness in many AI-for-code models, i.e. models not capturing task-relevant signals, they do not offer solutions to rectify this problem. In this paper, we explore data-driven approaches to enhance models' signal-awareness: 1) we combine the SE concept of code complexity with the AI technique of curriculum learning; 2) we incorporate SE assistance into AI models by customizing Delta Debugging to generate simplified signal-preserving programs, augmenting them to the training dataset. With our techniques, we achieve up to 4.8x improvement in model signal awareness. Using the notion of code complexity, we further present a novel model learning introspection approach from the perspective of the dataset.