Shijing Si

Shijing Si

Researcher

Shijing Si obtained his Ph.D. in Statistics from Imperial College London and subsequently conducted postdoctoral research in Lawrence Carin’s laboratory at Duke University in the United States. His primary research interests lie in statistical machine learning and artificial intelligence algorithms, with a particular focus on their real-world applications in finance, healthcare, and various other sectors. He held the position of Senior Algorithm Researcher at PAT (Shenzhen) Co., Ltd.

Interests
  • Artificial Intelligence
  • Voice Conversion
  • Talking Face

Publications

  1. On the Calibration and Uncertainty with Pólya-Gamma Augmentation for Dialog Retrieval Models (2023) In AAAI2023 (CCF-A)
  2. Boosting Star-GANs for Voice Conversion with Contrastive Discriminator, (2022), †First Author, In ICONIP2022 (CCF-C)
  3. Uncertainty Calibration for Deep Audio Classifiers (2022) In INTERSPEECH2022 (CCF-C)
  4. A Fair Federated Learning Framework With Reinforcement Learning (2022) In IJCNN2022 (CCF-C)
  5. A Nearest Neighbor Under-sampling Strategy for Vertical Federated Learning in Financial Domain (2022) In IH&MMSec2022 (CCF-C)
  6. Augmentation-induced Consistency Regularization for Classification (2022) In IJCNN2022 (CCF-C)
  7. Cali3F: Calibrated Fast Fair Federated Recommendation System (2022) In IJCNN2022 (CCF-C)
  8. Debias the Black-Box: A Fair Ranking Framework via Knowledge Distillation (2022) In WISE2022 (CCF-C)
  9. Federated Non-negative Matrix Factorization for Short Texts Topic Modeling with Mutual Information, (2022), †First Author, In IJCNN2022 (CCF-C)
  10. Federated Split BERT for Heterogeneous Text Classification (2022) In IJCNN2022 (CCF-C)
  11. Improving Human Image Synthesis with Residual Fast Fourier Transformation and Wasserstein Distance (2022) In IJCNN2022 (CCF-C)
  12. Leveraging Causal Inference for Explainable Automatic Program Repair, (2022), ✉Corresponding Author, In IJCNN2022 (CCF-C)
  13. Machine Unlearning Method Based On Projection Residual (2022) In DSAA2022 (CCF-C)
  14. Pose Guided Human Image Synthesis with Partially Decoupled GAN (2022) In ACML2022 (CCF-C)
  15. RL-MD: A Novel Reinforcement Learning Approach for DNA Motif Discovery (2022) In DSAA2022 (CCF-C)
  16. Towards Speaker Age Estimation With Label Distribution Learning, (2022), †First Author, In ICASSP2022 (CCF-B)
  17. VU-BERT: A Unified Framework for Visual Dialog (2022) In ICASSP2022 (CCF-B)
  18. zkMLaaS: a Verifiable Scheme for Machine Learning as a Service (2022) In GLOBECOM2022 (CCF-C)
  19. Speech2Video: Cross-Modal Distillation for Speech to Video Generation, (2021), †First Author, In INTERSPEECH2021 (CCF-C)
  20. Variational Information Bottleneck for Effective Low-Resource Audio Classification, (2021), †First Author, In INTERSPEECH2021 (CCF-C)
  21. Case Study of Few-Shot Learning in Text Recognition Models, (2021), ✉Corresponding Author, In WISE2021 (CCF-C)