activity
20122019
most citedAdversarial Examples on Graph Data: Deep Insights into Attack and Defense

104 citations · 153 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG2019104 cited

Adversarial Examples on Graph Data: Deep Insights into Attack and Defense

Huijun Wu, Chen Wang, Yuriy Tyshetskiy +3

Graph deep learning models, such as graph convolutional networks (GCN) achieve remarkable performance for tasks on graph data. Similar to other types of deep models, graph deep lea…

cs.LG201922 cited

Efficient Representation Learning Using Random Walks for Dynamic Graphs

Hooman Peiro Sajjad, Andrew Docherty, Yuriy Tyshetskiy

An important part of many machine learning workflows on graphs is vertex representation learning, i.e., learning a low-dimensional vector representation for each vertex in the grap…

cs.LG201813 cited

Evaluating approaches for supervised semantic labeling

Natalia Ruemmele, Yuriy Tyshetskiy, Alex Collins

Relational data sources are still one of the most popular ways to store enterprise or Web data, however, the issue with relational schema is the lack of a well-defined semantic des…

physics.plasm-ph20121 cited

Comment on "Novel Attractive Force between Ions in Quantum Plasmas" [Shukla, Eliasson, PRL 108, 165007 (2012), arXiv:1112.5556]

Yuriy O. Tyshetskiy, Sergey V. Vladimirov

It is shown that the attractive force between ions in a degenerate quantum plasma, recently predicted by Shukla and Eliasson [Shukla, Eliasson, PRL 108, 165007 (2012), arXiv:1112.5…

physics.plasm-ph201213 cited

Surface plasmon polaritons in a semi-bounded degenerate plasma: role of spatial dispersion and collisions

Yuriy Tyshetskiy, Sergey V. Vladimirov, Roman Kompaneets

Surface plasmon polaritons (SPPs) in a semi-bounded degenerate plasma (e.g., a metal) are studied using the quasiclassical mean-field kinetic model, taking into account the spatial…