Dr. Guang Wang, an Assistant Professor in the Computer Science Department, has two papers recently got accepted by the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2024). The annual ACM SIGKDD conference is the premier international forum for data mining researchers and practitioners from academia, industry, and government to share their ideas, research results and experiences. The acceptance rate of KDD 2024 is around 20%. For the paper titled “Paths2Pair: Meta-path Based Link Prediction in Billion-Scale Commercial Heterogeneous Graphs”, Dr. Guang Wang is the corresponding author. This paper introduces Paths2Pair, a novel framework to address these limitations for link prediction in billion-scale commercial heterogeneous graphs. (i) First, it selects a subset of reliable entity pairs for prediction based on relevant meta-paths.
(ii) It then utilizes various types of content information from the meta-paths between each selected entity pair to predict whether a target relation exists. Paths2Pair is evaluated on a large-scale dataset, and results show Paths2Pair outperforms state-of-the-art baselines significantly.
In another accepted KDD paper titled “Where have you been? A Study of Privacy Risk for Point-of-Interest Recommendation”, they designed a privacy attack suite containing data extraction and membership inference attacks tailored for point-of-interest (POI) recommendation models, one of the most widely used mobility data-based machine learning (ML) models. These attacks in their attack suite assume different adversary knowledge and aim to extract different types of sensitive information from mobility data, providing a holistic privacy risk assessment for POI recommendation models. Experimental evaluation using two real-world mobility datasets demonstrates that current POI recommendation models are vulnerable to our attacks. They also present unique findings to understand what types of mobility data are more susceptible to privacy attacks. Finally, they evaluate defenses against these attacks and highlight future directions and challenges.
The two papers were accepted by the ACM KDD 2024 and are set to be published by the ACM in the conference proceedings.