Precoder Learning for Weighted Sum Rate Maximization

2025-03-06

AI Summary

This paper addresses the weighted sum-rate maximization (WSRM) precoding optimization problem in multi-user MIMO systems. We propose an end-to-end learnable deep neural network that directly maps channel state information (CSI) and user weights to the optimal precoding matrix. Our key contribution is the first incorporation of joint unitary invariance and user-permutation equivariance into the network architecture, embedding physics-informed inductive biases that significantly improve generalization and training efficiency. Compared with existing learning-based precoding methods, our approach achieves higher accuracy and superior generalization across varying signal-to-noise ratios and numbers of users, while reducing both training and inference complexity. The resulting framework provides an efficient and practical paradigm for real-time precoding in integrated sensing and communication (ISAC) scenarios.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Deep Neural Architectures and Foundation Models
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Weighted sum rate maximization (WSRM) for precoder optimization effectively balances performance and fairness among users. Recent studies have demonstrated the potential of deep learning in precoder optimization for sum rate maximization. However, the WSRM problem necessitates a redesign of neural network architectures to incorporate user weights into the input. In this paper, we propose a novel deep neural network (DNN) to learn the precoder for WSRM. Compared to existing DNNs, the proposed DNN leverage the joint unitary and permutation equivariant property inherent in the optimal precoding policy, effectively enhancing learning performance while reducing training complexity. Simulation results demonstrate that the proposed method significantly outperforms baseline learning methods in terms of both learning and generalization performance while maintaining low training and inference complexity.

Problem

• Optimizes precoder for weighted sum rate maximization.
• Incorporates user weights into neural network design.
• Enhances learning performance with reduced complexity.

Innovation

• Novel DNN for weighted sum rate maximization
• Incorporates user weights into neural network input
• Leverages unitary and permutation equivariant properties