Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Khasahmadi, Amir Hosein"'
Autor:
Sanghi, Aditya, Fu, Rao, Liu, Vivian, Willis, Karl, Shayani, Hooman, Khasahmadi, Amir Hosein, Sridhar, Srinath, Ritchie, Daniel
Recent works have demonstrated that natural language can be used to generate and edit 3D shapes. However, these methods generate shapes with limited fidelity and diversity. We introduce CLIP-Sculptor, a method to address these constraints by producin
Externí odkaz:
http://arxiv.org/abs/2211.01427
Autor:
Chu, Hang, Khasahmadi, Amir Hosein, Willis, Karl D. D., Anderson, Fraser, Mao, Yaoli, Tran, Linh, Matejka, Justin, Vermeulen, Jo
User modeling is crucial to understanding user behavior and essential for improving user experience and personalized recommendations. When users interact with software, vast amounts of command sequences are generated through logging and analytics sys
Externí odkaz:
http://arxiv.org/abs/2207.14760
Devising augmentations for graph contrastive learning is challenging due to their irregular structure, drastic distribution shifts, and nonequivalent feature spaces across datasets. We introduce LG2AR, Learning Graph Augmentations to Learn Graph Repr
Externí odkaz:
http://arxiv.org/abs/2201.09830
Learning interpretable and human-controllable representations that uncover factors of variation in data remains an ongoing key challenge in representation learning. We investigate learning group-disentangled representations for groups of factors with
Externí odkaz:
http://arxiv.org/abs/2110.12185
Autor:
Taghanaki, Saeid Asgari, Hassani, Kaveh, Jayaraman, Pradeep Kumar, Khasahmadi, Amir Hosein, Custis, Tonya
Deep classifiers tend to associate a few discriminative input variables with their objective function, which in turn, may hurt their generalization capabilities. To address this, one can design systematic experiments and/or inspect the models via int
Externí odkaz:
http://arxiv.org/abs/2007.04525
We introduce a self-supervised approach for learning node and graph level representations by contrasting structural views of graphs. We show that unlike visual representation learning, increasing the number of views to more than two or contrasting mu
Externí odkaz:
http://arxiv.org/abs/2006.05582
Graph neural networks (GNNs) are a class of deep models that operate on data with arbitrary topology represented as graphs. We introduce an efficient memory layer for GNNs that can jointly learn node representations and coarsen the graph. We also int
Externí odkaz:
http://arxiv.org/abs/2002.09518