ChaosMining: A Benchmark to Evaluate Post-Hoc Local Attribution Methods in Low SNR Environments

TL;DR

A novel extension to the notable recursive feature elimination (RFE) algorithm is introduced, enhancing its applicability for neural networks and highlighting its strengths in prediction and feature selection, alongside limitations in scalability.

Abstract

In this study, we examine the efficacy of post-hoc local attribution methods in identifying features with predictive power from irrelevant ones in domains characterized by a low signal-to-noise ratio (SNR), a common scenario in real-world machine learning applications. We developed synthetic datasets encompassing symbolic functional, image, and audio data, incorporating a benchmark on the {\it (Model \(\times\) Attribution\(\times\) Noise Condition)} triplet. By rigorously testing various classic models trained from scratch, we gained valuable insights into the performance of these attribution methods in multiple conditions. Based on these findings, we introduce a novel extension to the notable recursive feature elimination (RFE) algorithm, enhancing its applicability for neural networks. Our experiments highlight its strengths in prediction and feature selection, alongside limitations in scalability. Further details and additional minor findings are included in the appendix, with extensive discussions. The codes and resources are available at \href{https://github.com/geshijoker/ChaosMining/}{URL}.

Figures (10)

• Figure 1: A teaser figure of the approach (on the left) and challenge (on the right) of this work. In (a) and (c), the attributions are scalar weights assigned to features via a one-to-one mapping in a post-hoc manner. In (b) and (d), only one feature is predictive as defined by Equation \ref{['eq:0']}.
• Figure 2: The examples of synthetic vision data and saliency maps of attribution methods. The foreground images can be placed at a fixed position (center) across instances or randomly. The background images can be generated by Gaussian noise or images of flowers.
• Figure 3: The examples of sources to construct synthetic audio data. Figure (a) is the foreground predictive feature while (b) and (c) are background features that are irrelevant to the classification task.
• Figure 4: Experimental results on symbolic functional data using MLP regressors differentiated by varying factors. For each subplot, we only change one factor from the default configuration. $\blacktriangle$ denotes the UScore of the predictions. $\blacktriangledown$, $\blacksquare$, $\blacklozenge$, and $\bigstar$ denote the FPrec of SA, DL, IG, and FA methods respectively.
• Figure 5: The results of our simulation experiments. Convergence is quantified by the area under the FPrec curve across 300 training epochs, while consistency is assessed through the average agreement between the top-k most important features of a sample and the average importance of the entire dataset. Both convergence and consistency scores are normalized so that the value for SA is set to 1. Additionally, we report the average and standard deviation of the memory and time costs incurred at the test stage.

Theorems & Definitions (1)

• Definition 1