学术讲座

大数据管理与分析方法研究北京市重点实验室（BDAI）研究生沙龙由中国人民大学高瓴人工智能智能学院与信息学院联合定期举行，本周BDAI重点实验室研讨会由高瓴人工智能学院博士生何明国和信息学院博士生郭若杨分别介绍各自的研究工作。欢迎同学们积极参与研讨！

汇报人：何明国，博士二年级

时间：2021年11月3日 12：30-13：30

标题：BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation

摘要：Many representative graph neural networks, e.g., GPR-GNN and ChebNet approximate graph convolutions with graph spectral filters. However, existing work either applies predefined filter weights or learns them without necessary constraints, which may lead to oversimplified or ill-posed filters. To overcome these issues, we propose BernNet, a novel graph neural network with theoretical support that provides a simple but effective scheme for designing and learning arbitrary graph spectral filters. In particular, for any filter over the normalized Laplacian spectrum of a graph, our BernNet estimates it by an order-K Bernstein polynomial approximation and designs its spectral property by setting the coefficients of the Bernstein basis. Moreover, we can learn the coefficients (and the corresponding filter weights) based on observed graphs and their associated signals and thus achieve the BernNet specialized for the data. Our experiments demonstrate that BernNet can learn arbitrary spectral filters, including complicated band-rejection and comb filters, and it achieves superior performance in real-world graph modeling tasks.

汇报人：郭若杨，博士五年级

时间：2021年11月3日 12：30-13：30

标题：LuxGeo: Efficient and Secure Enhanced  Geometric Range Queries

摘要：As location-based applications flourishing, we will witness soon the transferring of a prodigious amount of data from the local to a public cloud. The rising demand for outsourced data is moving toward a wider geographical area with arbitrary distribution (i.e., dense or sparse) and query scope (i.e., limited or vast). The outsourced individual data should be preserved when being queried as facing cloud risks, especially for location information. Geometric range queries are one of the most fundamental search functions. However, the existed works of secure geometric queries are far from practical usage on efficiency and security simultaneously. In this paper, we propose a novel scheme, LuxGeo. Our scheme reaches a constant navigation and a linear sweep, which is tailored for secure and efficient location-lookup. Our experiments over three real-world spatial datasets have shown its practical efficiency. For example, it only takes 10:01s with 728 tuples retrieved over 63; 369 ciphertext dataset for a single query. LuxGeo has better performance than the existed solutions for a GSE problem on efficiency and security.