Yutong Lu

TL;DR: A Communicative Message Passing Neural Network (CMPNN) is proposed to improve the molecular embedding by strengthening the message interactions between nodes and edges through a communicative kernel.

TL;DR: A graph-based cascade feature extraction method based on transaction records and a lightGBM-based Dual-sampling Ensemble algorithm to build the identification model and extensive experiments show that the proposed algorithm can effectively identify phishing scams.

TL;DR: A set of hardware and software features effectively supporting high performance communications, ranging over remote direct memory access, collective optimization, hardware enable reliable end-to-end communication, user-level message passing services, etc, are highlighted.

TL;DR: This work implements a shared-memory implementation of Gauss-Seidel smoother on Xeon Phi that balances parallelism, data access locality, CG convergence rate, and communication overhead, and demonstrates that the optimizations not only benefit HPCG original dataset, which is based on structured 3D grid, but also a wide range of unstructured matrices.

TL;DR: A quasi-biogenic molecule generator (QBMG) is reported to compose virtual quasi- biogenic compound libraries by means of gated recurrent unit recurrent neural networks, which can be used to generate virtual compound libraries for pharmaceutical lead identification and optimization.