Journal
2020 ACM/IEEE 42ND INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE 2020)
Volume -, Issue -, Pages 986-998Publisher
IEEE COMPUTER SOC
DOI: 10.1145/3377811.3380423
Keywords
-
Categories
Funding
- DARPA [FA8650-15-C-7562]
- NSF [1748764, 1901242, 1910300]
- ONR [N000141410468, N000141712947]
- Sandia National Lab [1701331]
Ask authors/readers for more resources
Recurrent Neural Networks (RNN) can deal with (textual) input with various length and hence have a lot of applications in software systems and software engineering applications. RNNs depend on word embeddings that are usually pre-trained by third parties to encode textual inputs to numerical values. It is well known that problematic word embeddings can lead to low model accuracy. In this paper, we propose a new technique to automatically diagnose how problematic embeddings impact model performance, by comparing model execution traces from correctly and incorrectly executed samples. We then leverage the diagnosis results as guidance to harden/repair the embeddings. Our experiments show that TRADER can consistently and effectively improve accuracy for real world models and datasets by 5.37% on average, which represents substantial improvement in the literature of RNN models.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available