From f94ad1d10598c98848870d021993db3ec8dd92ef Mon Sep 17 00:00:00 2001 From: aver Date: Tue, 20 Aug 2024 20:13:31 +0100 Subject: [PATCH] typos --- _includes/footer/custom.html | 2 +- _publications/marconato2024bears.md | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/_includes/footer/custom.html b/_includes/footer/custom.html index 78128c6..5c020ba 100644 --- a/_includes/footer/custom.html +++ b/_includes/footer/custom.html @@ -45,7 +45,7 @@ "autonomous & provably reliable intelligent learners", "about probabilities, reasoning, integrals & logic", "alone pattern recognition
is
limited", - "adaptive pprograms requiring interactive learning", + "adaptive programs requiring interactive learning", "april is probably a recursive identifier of a lab" ]; diff --git a/_publications/marconato2024bears.md b/_publications/marconato2024bears.md index 4b93ffa..517e211 100644 --- a/_publications/marconato2024bears.md +++ b/_publications/marconato2024bears.md @@ -15,10 +15,10 @@ code: "https://github.com/samuelebortolotti/bears" excerpt: "NeSy models can suffer from reasoning shortcuts, and to make them shortcut-aware, we sprinkle a pinch of Bayes to quantify the uncertainty over the extracted concepts, showing it is correlated to the presence of reasoning shortcuts." abstract: "Neuro-Symbolic (NeSy) predictors that conform to symbolic knowledge - encoding, e.g., safety constraints - can be affected by Reasoning Shortcuts (RSs): They learn concepts consistent with the symbolic knowledge by exploiting unintended semantics. RSs compromise reliability and generalization and, as we show in this paper, they are linked to NeSy models being overconfident about the predicted concepts. Unfortunately, the only trustworthy mitigation strategy requires collecting costly dense supervision over the concepts. Rather than attempting to avoid RSs altogether, we propose to ensure NeSy models are aware of the semantic ambiguity of the concepts they learn, thus enabling their users to identify and distrust low-quality concepts. Starting from three simple desiderata, we derive bears (BE Aware of Reasoning Shortcuts), an ensembling technique that calibrates the model's concept-level confidence without compromising prediction accuracy, thus encouraging NeSy architectures to be uncertain about concepts affected by RSs. We show empirically that bears improves RS-awareness of several state-of-the-art NeSy models, and also facilitates acquiring informative dense annotations for mitigation purposes." supplemental: -bibtex: "@article{marconato2024bears,
+bibtex: "@inproceedings{marconato2024bears,
title={BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts},
author={Emanuele Marconato, Samuele Bortolotti, Emile van Krieken, Antonio Vergari, Andrea Passerini, Stefano Teso,
- journal={arXiv preprint arXiv:2402.12240},
+ booktitle={Uncertainty in Artificial Intelligence (UAI)},
year={2024} }" ---