J
Jiawei Han
Researcher at University of Illinois at Urbana–Champaign
Publications - 1302
Citations - 155054
Jiawei Han is an academic researcher from University of Illinois at Urbana–Champaign. The author has contributed to research in topics: Cluster analysis & Knowledge extraction. The author has an hindex of 168, co-authored 1233 publications receiving 143427 citations. Previous affiliations of Jiawei Han include Georgia Institute of Technology & United States Army Research Laboratory.
Papers
More filters
Proceedings ArticleDOI
Top-K interesting subgraph discovery in information networks
TL;DR: This paper introduces two index structures for the network: topology index, and graph maximum metapath weight index, which are both computed offline and proposes novel top-K mechanisms to exploit these indexes for answering interesting subgraph queries online efficiently.
Proceedings ArticleDOI
Detecting Recurring and Novel Classes in Concept-Drifting Data Streams
Mohammad M. Masud,Tahseen M. Al-Khateeb,Latifur Khan,Charu C. Aggarwal,Jing Gao,Jiawei Han,Bhavani Thuraisingham +6 more
TL;DR: This paper proposes a more realistic novel class detection technique, which remembers a class and identifies it as "not novel" when it reappears after a long disappearance, and has shown significant reduction in classification error over state-of-the-art stream classification techniques on several benchmark data streams.
Reference BookDOI
Next Generation of Data Mining
TL;DR: This volume surveys promising approaches to data mining problems that span an array of disciplines and discusses the impact of new technologies, such as the semantic web, on data mining and provides recommendations for privacy-preserving mechanisms.
Proceedings ArticleDOI
A Data-Driven Graph Generative Model for Temporal Interaction Networks
TL;DR: This work proposes an end-to-end deep generative framework named TagGen, which outperforms all baselines in the temporal interaction network generation problem, and significantly boosts the performance of the prediction models in the tasks of anomaly detection and link prediction.
Proceedings ArticleDOI
Text classification from positive and unlabeled documents
TL;DR: This paper explores an efficient extension of the standard Support Vector Machine approach, called SVMC (Support Vector Mapping Convergence) for the TC-WON tasks, and shows that when the positive training data is not too under-sampled, SVMC significantly outperforms other methods.