publications
publications in chronological order. generated by jekyll-scholar.
2021
- Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge DistillationarXiv preprint arXiv:2106.07849 2021
2020
- Parallel blockwise knowledge distillation for deep neural network compressionIEEE Transactions on Parallel and Distributed Systems 2020
- Craft distillation: Layer-wise convolutional neural network distillationIn 2020 7th IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)/2020 6th IEEE International Conference on Edge Computing and Scalable Cloud (EdgeCom) 2020
- Transfer Learning with Fine-grained Sparse Networks: From an Efficient Network PerspectiveIn The Resource-Constrained Machine Learning Workshop in conjunction with IEEE Conference on Machine Learning and Systems (MLSys’ 20) 2020
- Is pruning compression?: Investigating pruning via network layer similarityIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision 2020
2019
- Improving the energy efficiency of relational and NoSQL databases via query optimizationsSustainable Computing: Informatics and Systems 2019