AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Mixture of Concept Bottleneck Experts

Francesco De Santis, Gabriele Ciravegna, Giovanni De Felice, Arianna Casanova, Francesco Giannini, Michelangelo Diligenti, Johannes Schneider, Danilo Giordano, Mateo Espinosa Zarlenga, Pietro Barbiero

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Counterfactual and statistical explanations · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Symbolic M-CBE instead of Lin-M-CBE or MLP-M-CBE for recovering the true expressionM-CBE · Pendulum, MNIST-Arith., MAWPSTree Edit Distance: Pendulum 5.71 -> 0.00; MAWPS 15.00 -> 0.00Improved
use Boolean-expression predictors (CMR, DCR) when the concept set is large (ablation)concept bottleneck predictor · CUB200 and CIFAR10 (more than 100 concepts)error rate: near-100% errorHurt
use linear or symbolic experts instead of Boolean experts in high-dimensional concept spacesM-CBE · high-dimensional concept datasetsaccuracy: up to +65%Improved
increase the number of experts above one (ablation)M-CBE · AWA2-Incomplete, CUB200-Incomplete, MAWPSerror rate / MAEImproved
replace black-box MLP task predictor with structured Lin-M-CBE or Sym-M-CBE (ablation)M-CBE · classification and regression benchmarksaccuracy vs complexityImproved
expand symbolic operator vocabulary from {+,-} to the complete set (ablation)Sym-M-CBE · PendulumMAE: 3.80 -> 0.46Improved
expand symbolic operator vocabulary from {+,-} to {+,-,x} (ablation)Sym-M-CBE · MAWPSMAE: 2.73 -> 1.29Improved
expand symbolic operator vocabulary from medium to complete (ablation)Sym-M-CBE · MAWPSMAE: 1.29 -> 1.36No clear effect
use a finite set of experts instead of per-sample expression trees (LICEM) (ablation)Lin-M-CBE · CUB-200global interpretabilityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy