Resource-Constrained Affect Modelling via Variance Regularisation Pruning
For developers of affect-aware systems in resource-constrained environments, this work provides a pruning method that preserves cross-participant stability, addressing a known bottleneck in deploying affective models on edge devices.
The paper tackles the problem of balancing computational efficiency with robustness across diverse users in affective computing. The proposed Variance-Regularised Pruning (VR) method maintains competitive Concordance Correlation Coefficient (CCC) performance even at 80% sparsity without fine-tuning.
Affective computing systems are increasingly embedded in pervasive and interactive environments, such as adaptive games, assistive technologies, and resource-constrained platforms, where computational efficiency must be balanced with reliability across diverse users. Model pruning offers an effective way to reduce computational demands, yet existing approaches typically optimise for sparsity alone, without accounting for how parameter removal impacts robustness across individuals. In this work, we introduce Variance-Regularised Pruning (VR), a pruning framework that explicitly incorporates cross-participant stability into the sparsification process. Rather than relying solely on average prediction error, VR evaluates each connection based on its joint contribution to both prediction accuracy and variability across users, prioritising parameters that remain reliable under distributional differences. We evaluate the proposed approach on the AGAIN dataset, which includes arousal annotations collected across nine affect-eliciting game environments. Experimental results demonstrate that VR maintains competitive Concordance Correlation Coefficient (CCC) performance even at 80\% sparsity without additional fine-tuning, highlighting its suitability for deployment in real-world, resource-limited affect-aware systems. Overall, the proposed framework supports the development of compact, robust affective models that can operate reliably in real-world interactive environments.