Machine Learning Conference Papers (Code Attached)

C18. S. Shrestha and X. Fu, ‘‘Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach’’, ICLR 2024 (Source Code)

C17. S. Ibrahim, X. Fu, R. Hutchinson, and E. Seo, ‘‘Under-counted tensor completion with neural incorporation of attributes’’, ICML 2023 (Source Code)

C16. T. Nguyen, S. Ibrahim, and X. Fu ‘‘Deep Clustering with Incomplete Noisy Pairwise Annotations: A Geometric Regularization Approach’’, ICML 2023 (Source Code)

C15. S. Ibrahim, T. Nguyen, and X. Fu ‘‘Deep learning from crowdsourced labels: Coupled cross-entropy minimization, identifiability, and regularization’’, ICLR 2023 (Source Code)

C14. Q. Lyu and X. Fu ‘‘Provable subspace identification under post-nonlinear mixtures’’, The 36th Conference on Neural Information Processing Systems (NeuriPS 2022), accepted.

C13. Q. Lyu and X. Fu ‘‘On Finite-Sample Identifiability of Generalized Contrastive Learning-Based Nonlinear Independent Component Analysis’’, International Conference on Machine Learning (ICML 2022), accepted.

C12. Q. Lyu, X. Fu, W. Wang, and S. Lu, ‘‘Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective’’, arXiv Pre-print, June 2021. This work has been accepted to ICLR 2022 for spotlight presentation. (Source Code)

C11. S. Ibrahim and X. Fu, ‘‘Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix Factorization’’, International Conference on Machine Learning (ICML 2021), accepted (acceptance rate = 21%). (Source Code)

C10. E. Seo, R. Hutchinson, X. Fu, C. A. Li, T. Hallman, J. Kilbride, W. Robinson, ‘‘StatEcoNet: Statistical Ecology Neural Networks for Species Distribution Modeling’’, Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021 (acceptance rate = 21%).

C9. S. Ibrahim, X. Fu, N. Kargas, and K. Huang, ‘‘Crowdsourcing via Pairwise Co-occurrences: Identifiability and Algorithms’’, Thirty-third Conference on Neural Information Processing Systems (NeuriPS 2019), accepted (acceptance rate = 21%). (Source Code)

C8. K. Huang and X. Fu, ‘‘Detecting Overlapping and Correlated Communities: Identifiability and Algorithm’’, International Conference on Machine Learning (ICML 2019), accepted. (acceptance rate=23%).

C7. K. Huang, X. Fu, and N. D. Sidiropoulos, ‘‘Learning Hidden Markov Models from Pairwise Co-occurrences with Applications to Topic Modeling’’, accepted to ICML 2018 (acceptance rate = 25%).

C6. K. Huang, X. Fu, and N. D. Sidiropoulos, ‘‘On Convergence of Epanechnikov Mean Shift,’’ AAAI 2018 (acceptance rate = 25%).

C5. B. Yang, X. Fu, N. D. Sidiropoulos, and M. Hong, ‘‘Towards K-Means-Friendly Spaces: Simultaneous Deep Learning and Clustering’’, International Conference on Machine Learning (ICML 2017), accepted. (Source Code)

C4. X. Fu, K. Huang, O. Stretcu, H. Song, E.E. Papalexakis, P. Talukdar, N.D. Sidiropoulos, C. Faloutsos, T. Mitchell, and B. Poczos ‘‘BRAINZOOM: High Resolution Reconstruction from Multi-modal Brain Signals", SIAM International Conference on Data Mining (SDM 2017), April, 2017, Houston, Texas, USA.

C3. X. Fu , K. Huang, E.E. Papalexakis, H. Song, P. Talukdar, N. D. Sidiropoulos, C. Faloutsos, and T. Mitchell, ‘‘Efficient and Distributed Algorithms for Large-Scale Generalized Canonical Correlations Analysis’’, IEEE Internatial Conference on Data Mining (ICDM 2016), Dec. 2016, Barcelona, Spain. (Matlab Demo)

    • Here is a python implementation of the algorithm with support to missing values; Thanks to Adrian Benton (Johns Hopkins University) for the implementation.

C2. K. Huang*, X. Fu* (* equal contribution), and N. D. Sidiropoulos, ‘‘Anchor-Free Correlated Topic Modeling: Identifiability and Algorithm’’, Advances in Neural Information Processing Systems (NIPS 2016), Dec. 2016, Barcelona, Spain. (Matlab Demo)

C1. M. Gardner, K. Huang, E. E. Papalexakis, X. Fu, P. P. Talukdar, C. Faloutsos, N. D. Sidiropoulos, and T. Mitchell, ‘‘Translation Invariant Word Embeddings’’ in Conference on Empirical Methods in Natural Language Processing (EMNLP), 2015, Lisbon, Portugal. (matlab code, data)