More Like this

1. Direct Observation of Node-to-Node Communication in Zeolitic Imidazolate Frameworks

   https://doi.org/10.1021/jacs.8b06727  

   Pattengale, Brian; SantaLucia, Daniel J.; Yang, Sizhuo; Hu, Wenhui; Liu, Cunming; Zhang, Xiaoyi; Berry, John F.; Huang, Jier (September 2018, Journal of the American Chemical Society)
2. Direct Observation of Node-to-Node Communication in Zeolitic Imidazolate Frameworks

   Brian, P.; SANTALUCIA, D. J.; Yang, S.; Hu, W.; Liu, C.; Zhang, X.; Berry, J. F.; Huang, J. (September 2018, Journal of the American Chemical Society)
3. Graph Sanitation with Application to Node Classification

   https://doi.org/10.1145/3485447.3512180  

   Xu, Zhe; Du, Boxin; Tong, Hanghang (April 2022, Graph Sanitation with Application to Node Classification)

   The past decades have witnessed the prosperity of graph mining, with a multitude of sophisticated models and algorithms designed for various mining tasks, such as ranking, classification, clustering and anomaly detection. Generally speaking, the vast majority of the existing works aim to answer the following question, that is, given a graph, what is the best way to mine it? In this paper, we introduce the graph sanitation problem, to an- swer an orthogonal question. That is, given a mining task and an initial graph, what is the best way to improve the initially provided graph? By learning a better graph as part of the input of the mining model, it is expected to benefit graph mining in a variety of settings, ranging from denoising, imputation to defense. We formulate the graph sanitation problem as a bilevel optimization problem, and fur- ther instantiate it by semi-supervised node classification, together with an effective solver named GaSoliNe. Extensive experimental results demonstrate that the proposed method is (1) broadly appli- cable with respect to various graph neural network models and flexible graph modification strategies, (2) effective in improving the node classification accuracy on both the original and contaminated graphs in various perturbation scenarios. In particular, it brings up to 25% performance improvement over the existing robust graph neural network methods. 

   more » « less
4. Paths to Fast Barrier Synchronization on the Node

   https://doi.org/10.1145/3307681.3325402  

   Hetland, Conor; Tziantzioulis, Georgios; Suchy, Brian; Leonard, Michael; Han, Jin; Albers, John; Hardavellas, Nikos; Dinda, Peter (June 2019, Proceedings of the 28th ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC))
5. On Generalizing Static Node Embedding to Dynamic Settings

   https://doi.org/10.1145/3488560.3498428  

   Jin, Di; Kim, Sungchul; Rossi, Ryan A.; Koutra, Danai (February 2022, WSDM '22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining)