Plant biodiversity is often correlated with ecosystem functioning in terrestrial ecosystems. However, we know little about the relative and combined effects of above- and belowground biodiversity on multiple ecosystem functions (for example, ecosystem multifunctionality, EMF) or how climate might mediate those relationships. Here we tease apart the effects of biotic and abiotic factors, both above- and belowground, on EMF on the Tibetan Plateau, China. We found that a suite of biotic and abiotic variables account for up to 86% of the variation in EMF, with the combined effects of above- and belowground biodiversity accounting for 45% of the variation in EMF. Our results have two important implications: first, including belowground biodiversity in models can improve the ability to explain and predict EMF. Second, regional-scale variation in climate, and perhaps climate change, can determine, or at least modify, the effects of biodiversity on EMF in natural ecosystems.

No abstract

Recent advances in neural networks have inspired people to design hybrid recommendation algorithms that can incorporate both (1) user-item interaction information and (2) content information including image, audio, and text. Despite their promising results, neural network-based recommendation algorithms pose extensive computational costs, making it challenging to scale and improve upon. In this paper, we propose a general neural network-based recommendation framework, which subsumes several existing stateof-the-art recommendation algorithms, and address the efficiency issue by investigating sampling strategies in the stochastic gradient descent training for the framework. We tackle this issue by first establishing a connection between the loss functions and the useritem interaction bipartite graph, where the loss function terms are defined on links while major computation burdens are located at nodes. We call this type of loss functions "graph-based" loss functions, for which varied mini-batch sampling strategies can have different computational costs. Based on the insight, three novel sampling strategies are proposed, which can significantly improve the training efficiency of the proposed framework (up to ×30 times speedup in our experiments), as well as improving the recommendation performance. Theoretical analysis is also provided for both the computational cost and the convergence. We believe the study of sampling strategies have further implications on general graphbased loss functions, and would also enable more research under the neural network-based recommendation framework.