Search Results for author: Amir Hosein Khasahmadi

Found 6 papers, 3 papers with code

Learning Graph Augmentations to Learn Graph Representations

no code implementations24 Jan 2022 Kaveh Hassani, Amir Hosein Khasahmadi

Devising augmentations for graph contrastive learning is challenging due to their irregular structure, drastic distribution shifts, and nonequivalent feature spaces across datasets.

Contrastive Learning

Group-disentangled Representation Learning with Weakly-Supervised Regularization

no code implementations23 Oct 2021 Linh Tran, Amir Hosein Khasahmadi, Aditya Sanghi, Saeid Asgari

Learning interpretable and human-controllable representations that uncover factors of variation in data remains an ongoing key challenge in representation learning.

Disentanglement Transfer Learning

Learning Task-Relevant Features via Contrastive Input Morphing

no code implementations1 Jan 2021 Saeid Asgari, Kristy Choi, Amir Hosein Khasahmadi, Anirudh Goyal

A fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream classification task, without overfitting to spurious input features.

Representation Learning

PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing

1 code implementation9 Jul 2020 Saeid Asgari Taghanaki, Kaveh Hassani, Pradeep Kumar Jayaraman, Amir Hosein Khasahmadi, Tonya Custis

We show that coupling a PointMask layer with an arbitrary model can discern the points in the input space which contribute the most to the prediction score, thereby leading to interpretability.

3D Point Cloud Classification Robust classification

Contrastive Multi-View Representation Learning on Graphs

3 code implementations ICML 2020 Kaveh Hassani, Amir Hosein Khasahmadi

We achieve new state-of-the-art results in self-supervised learning on 8 out of 8 node and graph classification benchmarks under the linear evaluation protocol.

General Classification Graph Classification +2

Memory-Based Graph Networks

2 code implementations ICLR 2020 Amir Hosein Khasahmadi, Kaveh Hassani, Parsa Moradi, Leo Lee, Quaid Morris

Graph neural networks (GNNs) are a class of deep models that operate on data with arbitrary topology represented as graphs.

Graph Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.