activity
20152022
most citedSet Representation Learning with Generalized Sliced-Wasserstein Embeddings

5 citations · 18 across the 9 of their papers we have counts for

collaborators

15 papers

cs.LG2022

A State-Augmented Approach for Learning Optimal Resource Management Decisions in Wireless Networks

Yiğit Berkay Uslu, Navid NaderiAlizadeh, Mark Eisen +1

We consider a radio resource management (RRM) problem in a multi-user wireless network, where the goal is to optimize a network-wide utility function subject to constraints on the…

cs.LG2022

Federated Representation Learning via Maximal Coding Rate Reduction

Juan Cervino, Navid NaderiAlizadeh, Alejandro Ribeiro

We propose a federated methodology to learn low-dimensional representations from a dataset that is distributed among several clients. In particular, we move away from the commonly-…

eess.SP20213 cited

Wireless Link Scheduling via Graph Representation Learning: A Comparative Study of Different Supervision Levels

Navid Naderializadeh

We consider the problem of binary power control, or link scheduling, in wireless interference networks, where the power control policy is trained using graph representation learnin…

cs.LG20215 cited

Set Representation Learning with Generalized Sliced-Wasserstein Embeddings

Navid Naderializadeh, Soheil Kolouri, Joseph F. Comer +2

An increasing number of machine learning tasks deal with learning representations from set-structured data. Solutions to these problems involve the composition of permutation-equiv…

eess.SP2020

Contrastive Self-Supervised Learning for Wireless Power Control

Navid Naderializadeh

We propose a new approach for power control in wireless networks using self-supervised learning. We partition a multi-layer perceptron that takes as input the channel matrix and ou…

cs.LG2020

Graph Convolutional Value Decomposition in Multi-Agent Reinforcement Learning

Navid Naderializadeh, Fan H. Hung, Sean Soleyman +1

We propose a novel framework for value function factorization in multi-agent deep reinforcement learning (MARL) using graph neural networks (GNNs). In particular, we consider the t…