NeFut Logo NeFut
Admin Login

[CS.AI] TRIPROBE: Probing Task Separability Beyond Classification for XAI

Published at: 2026-09-17 22:00 Last updated: 2026-09-18 00:46
#algorithm #AI #Machine Learning

Current evaluations of learning pipelines usually reduce to downstream accuracy, leaving the underlying reasons for task success or failure unexplored. TriProbe introduces a multi‑level probing framework that provides an explainable diagnosis of task separability. Instead of treating models as black boxes, it tracks how separability evolves across input space, learned features, and final classifier.

TriProbe decomposes a multi‑task problem into binary subtasks and applies three complementary probes:

The separability metric is the Maximum Fisher's Discriminant Ratio, defined as $$MFD = \frac{(\mu_1 - \mu_2)^2}{\sigma_1^2 + \sigma_2^2}$$ where $\mu_i$ and $\sigma_i^2$ denote the mean and variance of class $i$. This principled metric quantifies conflicts or bottlenecks at each level.

Experiments on the Roshambo sEMG benchmark demonstrate that TriProbe can uncover hidden breakdowns, guiding data collection, validation, and architecture design to address the identified issues.

Review

Original Source: https://arxiv.org/abs/2609.18525

[h] Back to Home