Department of Computer Science and Engineering
University at Buffalo
350 Davis Hall, Buffalo, NY 14260
Class-Distribution Regularized Consensus Maximization for Alleviating Overfitting in Model Combination. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, August 2014, to appear. Acceptance Rate: 151/1036 = 14.6%.
Resolving Conflicts in Heterogeneous Data by Truth Discovery and Source Reliability Estimation. ACM SIGMOD International Conference on Management of Data, Snowbird, UT, June 2014, to appear.
Outlier Detection for Temporal Data. Morgan & Claypool, Synthesis Lectures on Data Mining and Knowledge Discovery, March 2014.
Multi-Source Deep Learning for Information Trustworthiness Estimation. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Chicago, IL, August 2013, 766-774. Acceptance Rate: 126/726 = 17.4%.
On Handling Negative Transfer and Imbalanced Distributions in Multiple Source Transfer Learning. SIAM International Conference on Data Mining, Austin, TX, May 2013, 261-269. Acceptance Rate: 50/348 = 14.4%. Selected for publication in the special issue of "Best of SDM 2013" in Statistical Analysis and Data Mining