Jiawei Han

TL;DR: This work proposes a natural and effective way to resolve pattern-based classification by adopting discriminative patterns which are the prefix paths from root to nodes in tree-based models (e.g., random forest), which could perform as good as previous state-of-the-art algorithms, provide great interpretability by utilizing only very limited number of discriminating patterns, and predict new data extremely fast.

TL;DR: This tutorial presents an organized picture on scalable OLAP (online analytical processing) and mining of information networks, with the inclusion of the following topics: an introduction to information networks and information network analysis.

TL;DR: This paper proposes a novel joint representation learning module that allows simultaneous modeling of category dependencies, metadata information and textual semantics, and introduces a data augmentation module that hierarchically synthesizes training documents to complement the original, small-scale training set.

TL;DR: New techniques are developed by integrating the existing single-linear recursive query evaluation methods with the idea of side-relation unioned processing, which leads to a set of efficient query evaluation algorithms such as a side- correlation unioned transitive closure algorithm for the processing of Type I ML recursions.

TL;DR: CORD-NER as mentioned in this paper is a fine-grained named entity recognized dataset of COVID-19 literature, which contains over 12 million sentences annotated via distant supervision and includes 2,000 manually-curated sentences as a test set for performance evaluation.