92 citations · 252 across the 14 of their papers we have counts for
15 papers
Demystifying What Code Summarization Models Learned
Yu Wang, Ke Wang
Study patterns that models have learned has long been a focus of pattern recognition research. Explaining what patterns are discovered from training data, and how patterns are gene…
Combating fake news by empowering fact-checked news spread via topology-based interventions
Ke Wang, Waheeb Yaqub, Abdallah Lakhdari +1
Rapid information diffusion and large-scaled information cascades can enable the undesired spread of false information. A small-scaled false information outbreak may potentially le…
WheaCha: A Method for Explaining the Predictions of Models of Code
Yu Wang, Ke Wang, Linzhang Wang
Attribution methods have emerged as a popular approach to interpreting model predictions based on the relevance of input features. Although the feature importance ranking can provi…
Echelon: Two-Tier Malware Detection for Raw Executables to Reduce False Alarms
Anandharaju Durai Raju, Ke Wang
Existing malware detection approaches suffer from a simplistic trade-off between false positive rate (FPR) and true positive rate (TPR) due to a single tier classification approach…
Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation
Chaochao Lu, Biwei Huang, Ke Wang +3
Reinforcement learning (RL) algorithms usually require a substantial amount of interaction data and perform well only for specific tasks in a fixed environment. In some scenarios s…
On the Generalizability of Neural Program Models with respect to Semantic-Preserving Program Transformations
Md Rafiqul Islam Rabin, Nghi D. Q. Bui, Ke Wang +3
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 pred…