Probing Graph Representations

1 code implementation • 7 Mar 2023 • Mohammad Sadegh Akhondzadeh, Vijay Lingam, Aleksandar Bojchevski

Our findings on molecular datasets show the potential of probing for understanding the inductive biases of graph-based models.

Evaluating Sparse Interpretable Word Embeddings for Biomedical Domain

1 code implementation • 11 May 2020 • Mohammad Amin Samadi, Mohammad Sadegh Akhondzadeh, Sayed Jalal Zahabi, Mohammad Hossein Manshaei, Zeinab Maleki, Payman Adibi

Qualitative and quantitative measurements and metrics for interpretability of word vector representations are provided.

Word Embeddings

Wide-AdGraph: Detecting Ad Trackers with a Wide Dependency Chain Graph

1 code implementation • 29 Apr 2020 • Amir Hossein Kargaran, Mohammad Sadegh Akhondzadeh, Mohammad Reza Heidarpour, Mohammad Hossein Manshaei, Kave Salamatian, Masoud Nejad Sattary

In this work, we seek to simplify the update of these filter lists by combining different websites through a large-scale graph connecting all resource requests made over a large set of sites.

Blocking Graph Representation Learning +1