23 citations · 30 across the 3 of their papers we have counts for
4 papers
An Analysis Of Entire Space Multi-Task Models For Post-Click Conversion Prediction
Conor O'Brien, Kin Sum Liu, James Neufeld +2
Industrial recommender systems are frequently tasked with approximating probabilities for multiple, often closely related, user actions. For example, predicting if a user will clic…
Layered Graph Embedding for Entity Recommendation using Wikipedia in the Yahoo! Knowledge Graph
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, learn…
Topology Based Scalable Graph Kernels
Kin Sum Liu, Chien-Chun Ni, Yu-Yao Lin +1
We propose a new graph kernel for graph classification and comparison using Ollivier Ricci curvature. The Ricci curvature of an edge in a graph describes the connectivity in the lo…
Performing Co-Membership Attacks Against Deep Generative Models
Kin Sum Liu, Chaowei Xiao, Bo Li +1
In this paper we propose a new membership attack method called co-membership attacks against deep generative models including Variational Autoencoders (VAEs) and Generative Adversa…