12 papers · 1 filter
Oruga: An Avatar of Representational Systems Theory
Daniel Raggi, Gem Stapleton, Mateja Jamnik +3
Humans use representations flexibly. We draw diagrams, change representations and exploit creative analogies across different domains. We want to harness this kind of power and end…
Structure Transfer: an Inference-Based Calculus for the Transformation of Representations
Daniel Raggi, Gem Stapleton, Mateja Jamnik +3
Representation choice is of fundamental importance to our ability to communicate and reason effectively. A major unsolved problem, addressed in this paper, is how to devise represe…
Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
Mateo Espinosa Zarlenga, Gabriele Dominici, Pietro Barbiero +2
In this paper, we investigate how concept-based models (CMs) respond to out-of-distribution (OOD) inputs. CMs are interpretable neural architectures that first predict a set of hig…
Foundations of Interpretable Models
Pietro Barbiero, Mateo Espinosa Zarlenga, Alberto Termine +2
We argue that existing definitions of interpretability are not actionable in that they fail to inform users about general, sound, and robust interpretable model design. This makes…
Do Concept Bottleneck Models Respect Localities?
Naveen Raman, Mateo Espinosa Zarlenga, Juyeon Heo +1
Concept-based explainability methods use human-understandable intermediaries to produce explanations for machine learning models. These methods assume concept predictions can help…
Multimodal Lego: Model Merging and Fine-Tuning Across Topologies and Modalities in Biomedicine
Konstantin Hemker, Nikola Simidjievski, Mateja Jamnik
Learning holistic computational representations in physical, chemical or biological systems requires the ability to process information from different distributions and modalities…