Graph Neural Networks (GNNs) have achieved state of the art performance in node classification, regression, and recommendation tasks. GNNs work well when high-quality and rich connectivity structure is available. However, this requirement is not satisfied in many real world graphs where the node degrees have power-law distributions as many nodes have either fewer or noisy connections. The extreme case of this situation is a node may have no neighbors at all, called Strict Cold Start (SCS) scenario. This forces the prediction models to rely completely on the node's input features. We propose Cold Brew to address the SCS and noisy neighbor setting compared to pointwise and other graph-based models via a distillation approach. We introduce feature-contribution ratio (FCR), a metric to study the viability of using inductive GNNs to solve the SCS problem and to select the best architecture for SCS generalization. We experimentally show FCR disentangles the contributions of various components of graph datasets and demonstrate the superior performance of Cold Brew on several public benchmarks and proprietary e-commerce datasets. The source code for our approach is available at: https: //github.com/amazon-research/gnn-tail-generalization.

No abstract

Dry completion by means of a surface wellhead platform is a viable alternative to subsea wet completion in all water depths. Dry completion offers the benefits of better reservoir testing and monitoring, drilling and workover capabilities, lower operating costs due to ease of well intervention, better flow assurance, and increased recovery of oil and gas. This paper evaluates a variety of dry tree platform concepts, including both the established Spar and TLP and several newly developed platform concepts, for application in the Gulf of Mexico, offshore West Africa and Brazil. A single column medium draft floater, three and four column extended base TLPs are the new concepts that are included in this paper. A wide range of payloads is considered. Main particulars, global performance characteristics, advantages, and limitations and cost saving features of the new concepts are presented. Using the results from a screening study, trends in the global response, weights and costs are presented and discussed. A map of application domains for the dry tree platform concept is presented on the basis of cost comparisons.