activity
20182021
most citedGCN-LASE: Towards Adequately Incorporating Link Attributes in Graph Convolutional Networks

3 citations · 3 across the 2 of their papers we have counts for

collaborators

5 papers

cs.LG2021

HamNet: Conformation-Guided Molecular Representation with Hamiltonian Neural Networks

Ziyao Li, Shuwen Yang, Guojie Song +1

Well-designed molecular representations (fingerprints) are vital to combine medical chemistry and deep learning. Whereas incorporating 3D geometry of molecules (i.e. conformations)…

cs.SI2020

Learning Node Representations from Noisy Graph Structures

Junshan Wang, Ziyao Li, Qingqing Long +3

Learning low-dimensional representations on graphs has proved to be effective in various downstream tasks. However, noises prevail in real-world networks, which compromise networks…

cs.IR2019

A Novel User Representation Paradigm for Making Personalized Candidate Retrieval

Zheng Liu, Yu Xing, Jianxun Lian +3

Candidate retrieval is a fundamental issue in recommendation system. Given user's recommendation request, relevant candidates need to be retrieved in realtime for subsequent rankin…

cs.LG20193 cited

GCN-LASE: Towards Adequately Incorporating Link Attributes in Graph Convolutional Networks

Ziyao Li, Liang Zhang, Guojie Song

Graph Convolutional Networks (GCNs) have proved to be a most powerful architecture in aggregating local neighborhood information for individual graph nodes. Low-rank proximities an…

cs.LG2018

SepNE: Bringing Separability to Network Embedding

Ziyao Li, Liang Zhang, Guojie Song

Many successful methods have been proposed for learning low dimensional representations on large-scale networks, while almost all existing methods are designed in inseparable proce…