# Wireless Power Control via Counterfactual Optimization of Graph Neural Networks

arXiv: https://arxiv.org/abs/2002.07631 · HTML: https://mlsanity.com/paper/2002.07631/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Feb 2020.

## Built on by (most cited first, 10 of 10)

- [Counterfactual Learning on Graphs: A Survey](https://mlsanity.com/paper/2304.01391/) (2023)
- [Graph-based Deep Learning for Communication Networks: A Survey](https://mlsanity.com/paper/2106.02533/) (2021)
- [Learning Resilient Radio Resource Management Policies with Graph Neural Networks](https://mlsanity.com/paper/2203.11012/) (2022)
- [State-Augmented Learnable Algorithms for Resource Management in Wireless Networks](https://mlsanity.com/paper/2207.02242/) (2022)
- [Modular Meta-Learning for Power Control via Random Edge Graph Neural Networks](https://mlsanity.com/paper/2108.13178/) (2021)
- [Fast Power Control Adaptation via Meta-Learning for Random Edge Graph Neural Networks](https://mlsanity.com/paper/2105.00459/) (2021)
- [Wireless Link Scheduling via Graph Representation Learning: A Comparative Study of Different Supervision Levels](https://mlsanity.com/paper/2110.01722/) (2021)
- [Power Control with QoS Guarantees: A Differentiable Projection-based Unsupervised Learning Framework](https://mlsanity.com/paper/2306.01787/) (2023)
- [Learning Ad Hoc Network Dynamics via Graph-Structured World Models](https://mlsanity.com/paper/2604.14811/) (2026)
- [Weighted Sum-Rate Maximization With Causal Inference for Latent Interference Estimation](https://mlsanity.com/paper/2211.08327/) (2022)

## Abstract (arXiv)

We consider the problem of downlink power control in wireless networks, consisting of multiple transmitter-receiver pairs communicating with each other over a single shared wireless medium. To mitigate the interference among concurrent transmissions, we leverage the network topology to create a graph neural network architecture, and we then use an unsupervised primal-dual counterfactual optimization approach to learn optimal power allocation decisions. We show how the counterfactual optimization technique allows us to guarantee a minimum rate constraint, which adapts to the network size, hence achieving the right balance between average and 5th percentile user rates throughout a range of network configurations.