The shape of the wavefront is important for the most realistic reproduction of the acoustic wave. In acoustics, the wave front (or wave surface) is defined as the totality of points in the space of the propagating med...
详细信息
The petrochemical industry is composed of several interconnected processes that use fossil-based feedstock for producing chemicals. These processes are typically geographically clustered and often belong to different ...
详细信息
The introduction of electric buses has played a major role in reducing carbon dioxide emissions. The energy consumed by electric bus operation fluctuates. This fluctuation makes the optimization problem more difficult...
详细信息
The inventory routing problem simultaneously considers both the inventory problem and the delivery problem;it determines the amount of delivery of inventory and the delivery route such that the total cost is minimized...
详细信息
In this study, we addressed a unit commitment problem with uncertain demands during certain hours of the day. A chance-constrained stochastic mixed-integer program (SMIP) is used in the formulation to express the unce...
详细信息
Given the critical role of graphs in real-world applications and their high-security requirements, improving the ability of graph neural networks (GNNs) to detect out-of-distribution (OOD) data is an urgent research p...
详细信息
Given the critical role of graphs in real-world applications and their high-security requirements, improving the ability of graph neural networks (GNNs) to detect out-of-distribution (OOD) data is an urgent research problem. The recent work GNNSAFE (Wu et al., 2023) proposes a framework based on the aggregation of negative energy scores that significantly improves the performance of GNNs to detect node-level OOD data. However, our study finds that score aggregation among nodes is susceptible to extreme values due to the unboundedness of the negative energy scores and logit shifts, which severely limits the accuracy of GNNs in detecting node-level OOD data. In this paper, we propose NODESAFE: reducing the generation of extreme scores of nodes by adding two optimization terms that make the negative energy scores bounded and mitigate the logit shift. Experimental results show that our approach dramatically improves the ability of GNNs to detect OOD data at the node level, e.g., in detecting OOD data induced by Structure Manipulation, the metric of FPR95 (lower is better) in scenarios without (with) OOD data exposure are reduced from the current SOTA by 28.4% (22.7%). The code is available via https://***/ShenzhiYang2000/NODESAFE. Copyright 2024 by the author(s)
Projects are often executed under uncertain circumstances and require prior decisions that take uncertainty into account. Among them, the schedule of the initial plan and the plan for additional decisions correspondin...
详细信息
Event reasoning is a fundamental ability that underlies many applications. It requires event schema knowledge to perform global reasoning and needs to deal with the diversity of the inter-event relations and the reaso...
This research paper aims to address an optimization problem concerning production, logistics and maintenance in a complex fuel production system characterized by multiple machines, sites and customer demands. The key ...
详细信息
There are currently many discussions around the need to design infrastructure systems that are more resilient and sustainable in the future, especially considering growing uncertainties from climate change, pandemics,...
暂无评论