Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Equitable Multi-Task Learning for AI-RANs

Panayiotis Raptis, Fatih Aslan, George Iosifidis

TL;DR

An online-within-online fair multi-task learning (OWO-FMTL) framework that ensures long-term equity across users that guarantees diminishing performance disparity over time and operates with low computational overhead suitable for edge deployment is introduced.

Abstract

AI-enabled Radio Access Networks (AI-RANs) are expected to serve heterogeneous users with time-varying learning tasks over shared edge resources. Ensuring equitable inference performance across these users requires adaptive and fair learning mechanisms. This paper introduces an online-within-online fair multi-task learning (OWO-FMTL) framework that ensures long-term equity across users. The method combines two learning loops: an outer loop updating the shared model across rounds and an inner loop rebalancing user priorities within each round with a lightweight primal-dual update. Equity is quantified via generalized alpha-fairness, allowing a trade-off between efficiency and fairness. The framework guarantees diminishing performance disparity over time and operates with low computational overhead suitable for edge deployment. Experiments on convex and deep learning tasks confirm that OWO-FMTL outperforms existing multi-task learning baselines under dynamic scenarios.

Equitable Multi-Task Learning for AI-RANs

TL;DR

An online-within-online fair multi-task learning (OWO-FMTL) framework that ensures long-term equity across users that guarantees diminishing performance disparity over time and operates with low computational overhead suitable for edge deployment is introduced.

Abstract

AI-enabled Radio Access Networks (AI-RANs) are expected to serve heterogeneous users with time-varying learning tasks over shared edge resources. Ensuring equitable inference performance across these users requires adaptive and fair learning mechanisms. This paper introduces an online-within-online fair multi-task learning (OWO-FMTL) framework that ensures long-term equity across users. The method combines two learning loops: an outer loop updating the shared model across rounds and an inner loop rebalancing user priorities within each round with a lightweight primal-dual update. Equity is quantified via generalized alpha-fairness, allowing a trade-off between efficiency and fairness. The framework guarantees diminishing performance disparity over time and operates with low computational overhead suitable for edge deployment. Experiments on convex and deep learning tasks confirm that OWO-FMTL outperforms existing multi-task learning baselines under dynamic scenarios.
Paper Structure (6 sections, 1 theorem, 20 equations, 4 figures, 1 algorithm)

This paper contains 6 sections, 1 theorem, 20 equations, 4 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model and Problem Statement
  3. OWO Fair Learning Mechanism
  4. Performance Evaluation
  5. Conclusions and Future Work
  6. Appendix

Key Result

Theorem 1

Alg. algorithm achieves round-average fairness regret:

Figures (4)

  • Figure 1: Illustration of system's operation, where at each slot of a round all the participating users transmit the locally extracted features from their own data to the shared model. The shared model processes these features and send the results to the corresponding user, enabling them to complete their forward pass locally. Afterward, each user performs the backward pass, and the shared model aggregates and appropriately weights the received gradients to update its parameters (inner-loop). Once all slots within a round are completed, the shared model performs an additional autonomous update, preparing it for the next round (outer-loop).
  • Figure 2: Sublinear fairness regret of OWO-FMTL with respect to $m$, for $\alpha = 1$ (left) and $\alpha = 2$ (right), under both stochastic and adversarial environments.
  • Figure 3: Accumulated fairness (left) and utilities (right) across rounds.
  • Figure 4: Test losses on the validation data of each round.

Theorems & Definitions (1)

  • Theorem 1