1 code implementation • 17 Apr 2023 • Shweta Ann Jacob, Paul Louis, Amirali Salehi-Abari
To address the scalability issue while maintaining generalization, we propose Stochastic Subgraph Neighborhood Pooling (SSNP), which jointly aggregates the subgraph and its neighborhood (i. e., external topology) information without any computationally expensive operations such as labeling tricks.
3 code implementations • 29 Jan 2023 • Paul Louis, Shweta Ann Jacob, Amirali Salehi-Abari
Link prediction on graphs is a fundamental problem.
Ranked #1 on Link Property Prediction on ogbl-citation2
1 code implementation • 23 Jun 2022 • Paul Louis, Shweta Ann Jacob, Amirali Salehi-Abari
Graph neural networks have offered robust solutions for this problem, specifically by learning the representation of the subgraph enclosing the target link (i. e., pair of nodes).
no code implementations • 4 Nov 2021 • Alireza A. Namanloo, Julie Thorpe, Amirali Salehi-Abari
In this work, we first model peer assessment as multi-relational weighted networks that can express a variety of peer assessment setups, plus capture conflicts of interest and strategic behaviors.
1 code implementation • 13 Mar 2021 • Sarina Sajadi Ghaemmaghami, Amirali Salehi-Abari
These two problems are of interest to not only group recommendation, but also to personal privacy when the users intend to conceal their personal preferences but have participated in group decisions.
2 code implementations • 28 Feb 2021 • Aryan Asadian, Amirali Salehi-Abari
However, when there is a large difference between the model complexities of teacher and student (i. e., capacity gap), knowledge distillation loses its strength in transferring knowledge from the teacher to the student, thus training a weaker student.
1 code implementation • 17 Aug 2020 • Bahare Askari, Jaroslaw Szlichta, Amirali Salehi-Abari
We introduce joint variational autoencoders (JoVA), an ensemble of two VAEs, in which VAEs jointly learn both user and item representations and collectively reconstruct and predict user preferences.