activity
20092023
most citedLearning Heuristics over Large Graphs via Deep Reinforcement Learning

69 citations · 327 across the 44 of their papers we have counts for

collaborators
Showing 2020Show all

6 papers · 1 filter

cs.SI2020★ 2 cited

Expertise and confidence explain how social influence evolves along intellective tasks

Omid Askarisichani, Elizabeth Y. Huang, Abed K. Musaffar +3

Discovering the antecedents of individuals' influence in collaborative environments is an important, practical, and challenging problem. In this paper, we study interpersonal influ…

cs.LG2020

DANR: Discrepancy-aware Network Regularization

Hongyuan You, Furkan Kocayusufoglu, Ambuj K. Singh

Network regularization is an effective tool for incorporating structural prior knowledge to learn coherent models over networks, and has yielded provably accurate estimates in appl…

cs.SI2020

The 1995-2018 Global Evolution of the Network of Amicable and Hostile Relations Among Nation-States

Omid Askarisichania, Ambuj K. Singh, Francesco Bullo +1

We draw on the data collected by the Integrated Crisis Early Warning System on millions of international and regional public news stories, and this system's indicators of the orien…

cs.LG2020★ 9 cited

Learning Deep Graph Representations via Convolutional Neural Networks

Wei Ye, Omid Askarisichani, Alex Jones +1

Graph-structured data arise in many scenarios. A fundamental problem is to quantify the similarities of graphs for tasks such as classification. R-convolution graph kernels are pos…

cs.LG2020★ 4 cited

Incorporating User's Preference into Attributed Graph Clustering

Wei Ye, Dominik Mautz, Christian Boehm +2

Graph clustering has been studied extensively on both plain graphs and attributed graphs. However, all these methods need to partition the whole graph to find cluster structures. S…

cs.LG2020★ 19 cited

Tree++: Truncated Tree Based Graph Kernels

Wei Ye, Zhen Wang, Rachel Redberg +1

Graph-structured data arise ubiquitously in many application domains. A fundamental problem is to quantify their similarities. Graph kernels are often used for this purpose, which…