A Hilbert-Valued Functional Decomposition Framework for Explaining Time-Dependent Outputs

arXiv:2609.11295v1 Announce Type: cross Abstract: Feature-based explanations quantify features' influence on model predictions, but are primarily designed for scalar outputs. In many applications, however, outputs are functional or multivariate, such as time-dependent trajectories in demand forecasting. Consequently, existing approaches typically explain each output location independently, ignoring dependencies across the output components. We address this limitation by developing a unified framework for feature-based explanations of time-dependent outputs. Specifically, we generalize functional decomposition to Hilbert-valued prediction functions and extend an existing feature-based explanation framework to this setting. Our framework introduces kernel-based output representations that enable time-dependency-aware explanations at multiple levels of temporal granularity, including time-specific, time-resolved, and time-aggregated, while providing a unified view in which existing methods arise as special cases. We validate our framework on synthetic and real-world data, including intraday financial market volatility prediction and energy demand forecasting.

Related

• Semi-parametric Functional Classification via Path Signatures Logistic Regression with Adaptive Order Selection
• Towards A Unified Information Bottleneck Framework for Time Series Explanations
• HealthCAT: An Interpretable Encoder-only Transformer Framework for Health Indicator Prediction and Temporal Interpretation of Wearable Sensor Data
• Explaining Temporal Graph Neural Networks via Feature-induced Information Flow

Source: arXiv cs.LG | 2026-09-11