# Towards Bridging the FL Performance-Explainability Trade-Off: A Trustworthy 6G RAN Slicing Use-Case

arXiv: https://arxiv.org/abs/2307.12903 · HTML: https://mlsanity.com/paper/2307.12903/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 24 Jul 2023.

## Builds on (most cited first, 13 of 13)

- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Principles and Practice of Explainable Machine Learning](https://mlsanity.com/paper/2009.11698/) (2020)
- [Two-Player Games for Efficient Non-Convex Constrained Optimization](https://mlsanity.com/paper/1804.06500/) (2018)
- [Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints](https://mlsanity.com/paper/1807.00028/) (2018)
- [Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning](https://mlsanity.com/paper/2212.03954/) (2022)
- [Interpret Federated Learning with Shapley Values](https://mlsanity.com/paper/1905.04519/) (2019)
- [Evaluating explainable artificial intelligence methods for multi-label deep learning classification tasks in remote sensing](https://mlsanity.com/paper/2104.01375/) (2021)
- [Neuro-symbolic Explainable Artificial Intelligence Twin for Zero-touch IoE in Wireless Network](https://mlsanity.com/paper/2210.06649/) (2022)
- [Towards Ubiquitous AI in 6G with Federated Learning](https://mlsanity.com/paper/2004.13563/) (2020)
- [Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges](https://mlsanity.com/paper/2112.04698/) (2021)
- [Federated Orchestration for Network Slicing of Bandwidth and Computational Resource](https://mlsanity.com/paper/2002.02451/) (2020)
- [Knowledge-powered Explainable Artificial Intelligence (XAI) for Network Automation Towards 6G](https://mlsanity.com/paper/2205.05406/) (2022)
- [Quantifying Explainability in NLP and Analyzing Algorithms for Performance-Explainability Tradeoff](https://mlsanity.com/paper/2107.05693/) (2021)

## Built on by (most cited first, 2 of 2)

- [AI-Native Multi-Access Future Networks -- The REASON Architecture](https://mlsanity.com/paper/2411.06870/) (2024)
- [A Survey on AI for 6G: Challenges and Opportunities](https://mlsanity.com/paper/2604.02370/) (2026)

## Abstract (arXiv)

In the context of sixth-generation (6G) networks, where diverse network slices coexist, the adoption of AI-driven zero-touch management and orchestration (MANO) becomes crucial. However, ensuring the trustworthiness of AI black-boxes in real deployments is challenging. Explainable AI (XAI) tools can play a vital role in establishing transparency among the stakeholders in the slicing ecosystem. But there is a trade-off between AI performance and explainability, posing a dilemma for trustworthy 6G network slicing because the stakeholders require both highly performing AI models for efficient resource allocation and explainable decision-making to ensure fairness, accountability, and compliance. To balance this trade off and inspired by the closed loop automation and XAI methodologies, this paper presents a novel explanation-guided in-hoc federated learning (FL) approach where a constrained resource allocation model and an explainer exchange -- in a closed loop (CL) fashion -- soft attributions of the features as well as inference predictions to achieve a transparent 6G network slicing resource management in a RAN-Edge setup under non-independent identically distributed (non-IID) datasets. In particular, we quantitatively validate the faithfulness of the explanations via the so-called attribution-based confidence metric that is included as a constraint to guide the overall training process in the run-time FL optimization task. In this respect, Integrated-Gradient (IG) as well as Input × Gradient and SHAP are used to generate the attributions for our proposed in-hoc scheme, wherefore simulation results under different methods confirm its success in tackling the performance-explainability trade-off and its superiority over the unconstrained Integrated-Gradient post-hoc FL baseline.