Interpreting Neural Receivers: Mechanistic and Data Attribution Approaches

Tuononen, Marko

doi:10.24963/ijcai.2026/952

Interpreting Neural Receivers: Mechanistic and Data Attribution Approaches

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Doctoral Consortium. Pages 8347-8348.

https://doi.org/10.24963/ijcai.2026/952

Keywords

AI: AI Ethics, Trust, Fairnes
Machine Learning: Applications
Machine Learning: Explainable/Interpretable machine learning
Machine Learning: Representation learning

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.

Marko Tuononen. 2026. Interpreting Neural Receivers: Mechanistic and Data Attribution Approaches. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 8347–8348. https://doi.org/10.24963/ijcai.2026/952

@inproceedings{ijcai2026p952,
  title     = {Interpreting Neural Receivers: Mechanistic and Data Attribution Approaches},
  author    = {Tuononen, Marko},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {8347--8348},
  year      = {2026},
  month     = {8},
  note      = {Doctoral Consortium},
  doi       = {10.24963/ijcai.2026/952},
  url       = {https://doi.org/10.24963/ijcai.2026/952},
}

TY  - CPAPER
TI  - Interpreting Neural Receivers: Mechanistic and Data Attribution Approaches
AU  - Tuononen, Marko
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 8347
EP  - 8348
DO  - 10.24963/ijcai.2026/952
UR  - https://doi.org/10.24963/ijcai.2026/952
ER  -