Taoran Ji
Dr. Taoran Ji is an assistant professor of computer science at Texas A&M University-Corpus Christi. He is a machine learning expert with a passion for developing innovative techniques to solve real-world problems. Dr. Ji’s research interests include event detection, forecasting and impact analysis, time-series forecasting, and natural language processing. In addition to his research, Dr. Ji serves as a reviewer for several major machine learning conferences, such as AAAI, NeurIPS, ICLR, ICML, IJCAI, SIGSPATIAL, PAKDD, ECML, PKDD, and ITSC.
Prior to this, he served as the Director of Machine Learning at Moody’s Analytics, where he applied his expertise in machine learning and sequential data modeling to solve real-world problems in areas such as credit risk analysis and adverse media screening.
Dr. Ji received his Ph.D. in Computer Science from Virginia Tech in 2022 under the guidance of his advisor, Chang-Tien Lu. He has published his research results in major conferences such as AAAI, IJCAI, CIKM, BigData, ASONAM, and SIGSPATIAL. He has developed a set of new techniques that are used in different real-world scenarios, including horizon scanning of transformative technologies, cybersecurity event detection, and airport threat detection.
News
Apr 1, 2024 | One paper is accepted by NAACL. |
---|---|
Feb 12, 2024 | One paper is accepted by the Transactions on Knowledge Discovery from Data (TKDD). |
Oct 1, 2023 | One paper is accepted by IEEE BigData. |
Sep 1, 2023 | One paper is accepted by ACM Computing Surveys (ACUS). |
Aug 1, 2023 | I will be reviewing for ICLR and One paper is accepted by ASONAM. |
Selected Publications
-
Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural NetworksACM Comput. Surv., Dec 2023
-
Stock Movement and Volatility Prediction from Tweets, Macroeconomic Factors and Historical PricesIn 2023 IEEE International Conference on Big Data (Big Data), Dec 2023
-
LERTA-Net: A Temporal Distance-Aware Recurrent Networks for Stock Movement and Volatility PredictionIn Proceedings of The 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), Dec 2023
-
A Hierarchical Attention Graph Convolutional Network for Traffic Incident Impact ForecastingIn 2021 IEEE International Conference on Big Data (Big Data), Dec 2021
-
Bridging the gap between spatial and spectral domains: A survey on graph neural networksarXiv preprint arXiv:2002.11867, Dec 2020
-
Dynamic Multi-Context Attention Networks for Citation Forecasting of Scientific PublicationsProceedings of the AAAI Conference on Artificial Intelligence, May 2021
-
Feature Driven Learning Framework for Cybersecurity Event DetectionIn Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, May 2020
-
TITAN: A Spatiotemporal Feature Learning Framework for Traffic Incident Duration PredictionIn Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, May 2019
-
Batman or the Joker? The Powerful Urban Computing and Its Ethics IssuesSIGSPATIAL Special, Dec 2019
-
Multi-Task Learning for Transit Service Disruption DetectionIn 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), Aug 2018
-
Patent Citation Dynamics Modeling via Multi-Attention Recurrent NetworksIn Proceedings of the 28th International Joint Conference on Artificial Intelligence, Aug 2019