More Like this

1. Adaptive quantum/molecular mechanics: what have we learned, where are we, and where do we go from here?: Adaptive QM/MM

   https://doi.org/10.1002/wcms.1310  

   Duster, Adam W. ; Wang, Chun-Hung ; Garza, Christina M. ; Miller, Danielle E. ; Lin, Hai ( September 2017 , Wiley Interdisciplinary Reviews: Computational Molecular Science)
2. Simulation for Cyber Risk Management – Where are we, and Where do we Want to Go?

   https://doi.org/10.1109/WSC40007.2019.9004688  

   Shetty, Sachin ; Ray, Indrajit ; Ceilk, Nurcin ; Mesham, Michael ; Bastian, Nathaniel ; Zhu, Quanyan ( December 2019 , 2019 Winter Simulation Conference, WSC 2019)

   null (Ed.)
3. The National Environmental Policy Act and the USDA Forest Service: Where We Agree, Where We Disagree, and Why

   https://doi.org/10.1093/jofore/fvab076  

   Fleischman, Forrest ; Struthers, Cory ; Arnold, Gwen ; Dockry, Michael J. ; Scott, Tyler ( January 2022 , Journal of Forestry)

   In this article, we respond to a critique of our earlier work examining the USDA Forest Service’s (USFS’s) planning processes. We appreciate that our critics introduce new data to the discussion of USFS planning. Further data integration is a promising path to developing a deeper understanding of agency activities. Our critics’ analysis largely supports our original claims. Our most important difference is in our conceptualization of the planning process’s relationship to agency goals. Although our critics conceive of the USFS’s legally prescribed planning processes as a barrier to land management activities, we believe that public comment periods, scientific analysis, and land management activities are tools the agency uses to achieve its goals of managing land in the public interest.

   Study Implications: The USDA Forest Service’s current planning process has been critiqued as a barrier to accomplishing land management activities, but it is also an important tool for insuring science-based management and understanding public values and interests that the agency is legally bound to uphold.

    

   more » « less
4. Abstract Graph Neural Networks (GNNs) have shown satisfying performance on various graph learning tasks. To achieve better fitting capability, most GNNs are with a large number of parameters, which makes these GNNs computationally expensive. Therefore, it is difficult to deploy them onto edge devices with scarce computational resources, e.g., mobile phones and wearable smart devices. Knowledge Distillation (KD) is a common solution to compress GNNs, where a light-weighted model (i.e., the student model) is encouraged to mimic the behavior of a computationally expensive GNN (i.e., the teacher GNN model). Nevertheless, most existing GNN-based KD methods lack fairness consideration. As a consequence, the student model usually inherits and even exaggerates the bias from the teacher GNN. To handle such a problem, we take initial steps towards fair knowledge distillation for GNNs. Specifically, we first formulate a novel problem of fair knowledge distillation for GNN-based teacher-student frameworks. Then we propose a principled framework named RELIANT to mitigate the bias exhibited by the student model. Notably the design of RELIANT is decoupled from any specific teacher and student model structures, and thus can be easily adapted to various GNN-based KD frameworks. We perform extensive experiments on multiple real-world datasets, which corroborates that RELIANT achieves less biased GNN knowledge distillation while maintaining high prediction utility. Open-source code can be found at https://github.com/yushundong/RELIANT.

   Dong, Yushun ; Zhang, Binichi ; Yuan, Yiling ; Zou, Na ; Wang, Qi ; Li, Jundong ( January 2023 , Proceedings of the 2023 SIAM International Conference on Data Mining (SDM))
5. Gene Drive for Mosquito Control: Where Did It Come from and Where Are We Headed?

   https://doi.org/10.3390/ijerph14091006  

   Macias, Vanessa ; Ohm, Johanna ; Rasgon, Jason ( September 2017 , International Journal of Environmental Research and Public Health)