activity
20182023
most citedOn Proximity and Structural Role-based Embeddings in Networks: Misconceptions, Techniques, and Applications

79 citations · 364 across the 27 of their papers we have counts for

collaborators
Showing 2020Show all

6 papers · 1 filter

cs.SI2020

Heterogeneous Graphlets

Ryan A. Rossi, Nesreen K. Ahmed, Aldo Carranza +4

In this paper, we introduce a generalization of graphlets to heterogeneous networks called typed graphlets. Informally, typed graphlets are small typed induced subgraphs. Typed gra…

cs.LG2020

Graph Deep Factors for Forecasting

Hongjie Chen, Ryan A. Rossi, Kanak Mahadik +2

Deep probabilistic forecasting techniques have recently been proposed for modeling large collections of time-series. However, these techniques explicitly assume either complete ind…

cs.CL2020★ 4 cited

Learning Contextualized Knowledge Structures for Commonsense Reasoning

Jun Yan, Mrigank Raman, Aaron Chan +6

Recently, knowledge graph (KG) augmented models have achieved noteworthy success on various commonsense reasoning tasks. However, KG edge (fact) sparsity and noisy edge extraction/…

cs.CL2020★ 9 cited

Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation

Mrigank Raman, Aaron Chan, Siddhant Agarwal +7

Knowledge graphs (KGs) have helped neural models improve performance on various knowledge-intensive tasks, like question answering and item recommendation. By using attention over…

cs.IR2020★ 11 cited

ML-based Visualization Recommendation: Learning to Recommend Visualizations from Data

Xin Qian, Ryan A. Rossi, Fan Du +5

Visualization recommendation seeks to generate, score, and recommend to users useful visualizations automatically, and are fundamentally important for exploring and gaining insight…

cs.LG2020★ 2 cited

From Static to Dynamic Node Embeddings

Di Jin, Sungchul Kim, Ryan A. Rossi +1

We introduce a general framework for leveraging graph stream data for temporal prediction-based applications. Our proposed framework includes novel methods for learning an appropri…