Extreme Learning Machine for Graph Signal Processing
This work addresses regression tasks in graph signal processing, particularly under data scarcity and noise, but it is incremental as it builds on existing extreme learning machine methods.
The authors tackled the problem of improving extreme learning machines for regression tasks by incorporating graph signal processing-based regularization, assuming the target signal is a graph signal, and found that this regularization significantly helps when training data is limited and noisy, as confirmed by simulation results with real data.
In this article, we improve extreme learning machines for regression tasks using a graph signal processing based regularization. We assume that the target signal for prediction or regression is a graph signal. With this assumption, we use the regularization to enforce that the output of an extreme learning machine is smooth over a given graph. Simulation results with real data confirm that such regularization helps significantly when the available training data is limited in size and corrupted by noise.