[
    {
        "id": "osp-21565",
        "type": "article-journal",
        "title": "Importance-Aware Feature Sparsification for Wireless Split Learning",
        "author": [
            {
                "family": "Kim",
                "given": "Bum Jun"
            },
            {
                "family": "Huh",
                "given": "Yoon"
            },
            {
                "family": "Choi",
                "given": "Wan"
            }
        ],
        "URL": "https://omanscience.com/en/articles/importance-aware-feature-sparsification-for-wireless-split-learning",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Wireless split learning (SL) reduces on-device computation by offloading upper layers to a server, yet transmitting high-dimensional intermediate features at each iteration remains a major communication bottleneck. Existing methods select features at the client side using task-agnostic criteria such as magnitude, statistics, or clustering, which increases client-side processing and often degrades accuracy under non-independent and identically distributed (non-i.i.d.) client data. We propose importance-aware class-balanced sparsification (ICS), a lightweight approach in which the server ranks feature channels using Grad-CAM-based scores obtained from the true-class logit during backpropagation. The per-class scores are aggregated into a class-balanced, label-agnostic importance vector that mitigates head-class bias under label skew, and each client reuses this vector in the next round to retain the top-$N$ feature channels, incurring no additional client-side forward or backward passes. We further derive a non-asymptotic convergence bound that isolates the sparsification-induced error and characterizes how the sparsification ratio and mini-batch size jointly affect convergence under a fixed communication budget, and we analyze the communication and computational overhead of ICS against representative baselines. Beyond sequential CNN-based SL, we extend ICS to parallel split learning and to transformer-based models. Experiments show that ICS consistently outperforms the baselines, with larger gains under severe non-i.i.d. partitions."
    }
]