---
title: "Interpreting Neural Receivers: Mechanistic and Data Attribution Approaches"
authors:
  - "Marko Tuononen"
doi: "10.24963/ijcai.2026/952"
url: "https://ijcai.org/proceedings/2026/952"
pdf: "https://ijcai.org/proceedings/2026/0952.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "8347-8348"
track: "Doctoral Consortium"
keywords:
  - "AI: AI Ethics, Trust, Fairnes"
  - "Machine Learning: Applications"
  - "Machine Learning: Explainable/Interpretable machine learning"
  - "Machine Learning: Representation learning"
---

# Interpreting Neural Receivers: Mechanistic and Data Attribution Approaches

Marko Tuononen

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 8347-8348. DOI: [10.24963/ijcai.2026/952](https://doi.org/10.24963/ijcai.2026/952)

## Abstract

This research studies interpretability methods for deep neural network--based radio receivers in future wireless communication systems. The work focuses on representation-level analysis and training data attribution techniques that reveal how models encode physical-layer channel conditions and how training data influence receiver behavior. These insights enable validation, adaptation, and more trustworthy deployment of data-driven communication systems under realistic channel conditions, while providing deeper understanding of model behavior.