Scientific and Technological Resource Sharing Model Based on Few-Shot Relational Learning

Abstract

Resource sharing is to ensure required resources available for their demanders. However, due to the lack of proper sharing model, the current sharing rate of the scientific and technological resources is low, impeding technological innovation and value chain development. Here we propose a novel method to share scientific and technological resources by storing resources as nodes and correlations as links to form a complex network. We present a few-shot relational learning model to solve the coldstart and long-tail problems that are induced by newly added resources. Experimentally, using NELL-One and Wiki-One datasets, our one-shot results outperform the baseline framework -metaR by 40.2% and 4.1% on MRR in Pre-Train setting. We also show two practical applications, a resource graph and a resource map, to demonstrate how the complex network helps resource sharing.

Regressive Gaussian Process Latent Variable Model for Few-Frame Human Motion Prediction

“…An attractive solution is learning a "basis" of underlying knowledge by meta learning, and share it across a variety of motion types, including a brand-new action [13]- [16]. More concretely, this can be in principle achieved by that fine-tuning a pre-trained network from other tasks which have adequate labeled data [17]- [19], such as Meta-learning [20], [21], and so on. All these remarkable meta learning approaches have achieved great success.…”