no code implementations • 18 Aug 2021 • Conor O'Brien, Kin Sum Liu, James Neufeld, Rafael Barreto, Jonathan J Hunt
Industrial recommender systems are frequently tasked with approximating probabilities for multiple, often closely related, user actions.
no code implementations • 1 Jan 2021 • Ze Ye, Tengfei Ma, Chien-Chun Ni, Kin Sum Liu, Jie Gao, Chao Chen
We propose a novel GNN defense algorithm against structural attacks that maliciously modify graph topology.
no code implementations • ICLR 2020 • Ze Ye, Kin Sum Liu, Tengfei Ma, Jie Gao, Chao Chen
Graph-structured data is prevalent in many domains.
no code implementations • 15 Apr 2020 • Chien-Chun Ni, Kin Sum Liu, Nicolas Torzec
In this paper, we describe an embedding-based entity recommendation framework for Wikipedia that organizes Wikipedia into a collection of graphs layered on top of each other, learns complementary entity representations from their topology and content, and combines them with a lightweight learning-to-rank approach to recommend related entities on Wikipedia.
no code implementations • 15 Jul 2019 • Kin Sum Liu, Chien-Chun Ni, Yu-Yao Lin, Jie Gao
We propose a new graph kernel for graph classification and comparison using Ollivier Ricci curvature.
no code implementations • 24 May 2018 • Kin Sum Liu, Chaowei Xiao, Bo Li, Jie Gao
We conduct extensive experiments on a variety of datasets and generative models showing that: our attacker network outperforms prior membership attacks; co-membership attacks can be substantially more powerful than single attacks; and VAEs are more susceptible to membership attacks compared to GANs.