no code implementations • 29 Mar 2024 • Ali Behrouz, Michele Santacatterina, Ramin Zabih
Motivated by the success of SSMs, we present MambaMixer, a new architecture with data-dependent weights that uses a dual selection mechanism across tokens and channels, called Selective Token and Channel Mixer.
1 code implementation • 13 Feb 2024 • Ali Behrouz, Farnoosh Hashemi
Motivated by the recent success of State Space Models (SSMs), such as Mamba, we present Graph Mamba Networks (GMNs), a general framework for a new class of GNNs based on selective SSMs.
1 code implementation • NeurIPS 2023 • Ali Behrouz, Farnoosh Hashemi, Sadaf Sadeghian, Margo Seltzer
Our evaluation on 10 hypergraph benchmark datasets shows that CAT-Walk attains outstanding performance on temporal hyperedge prediction benchmarks in both inductive and transductive settings.
1 code implementation • 15 Mar 2023 • Farnoosh Hashemi, Ali Behrouz, Milad Rezaei Hajidehi
The evolution of these networks over time has motivated several recent studies to identify local communities in temporal networks.
1 code implementation • 15 Nov 2022 • Ali Behrouz, Margo Seltzer
The problem of identifying anomalies in dynamic networks is a fundamental task with a wide range of applications.
no code implementations • 17 Oct 2022 • Ali Behrouz, Farnoosh Hashemi
Existing CS approaches in multiplex networks adopt pre-defined subgraph patterns to model the communities, which cannot find communities that do not have such pre-defined patterns in real-world networks.
no code implementations • 13 Oct 2022 • Ali Behrouz, Mathias Lecuyer, Cynthia Rudin, Margo Seltzer
Specifically, they rely on the discreteness of the loss function, which means that real-valued weights cannot be directly used.