Focus in Explainable AI is shifting from explanations defined in terms o...
Self-explainable deep neural networks are a recent class of models that ...
In learning to defer, a predictor identifies risky decisions and defers ...
Neuro-Symbolic (NeSy) predictive models hold the promise of improved
com...
Neuro-symbolic predictors learn a mapping from sub-symbolic inputs to
hi...
We introduce Neuro-Symbolic Continual Learning, where a model has to sol...
Explanations have gained an increasing level of interest in the AI and
M...
We design a predictive layer for structured-output prediction (SOP) that...
Part-prototype Networks (ProtoPNets) are concept-based classifiers desig...
There is growing interest in concept-based models (CBMs) that combine
hi...
It is increasingly common to solve combinatorial optimisation problems t...
In this position paper, we study interactive learning for structured out...
Combinatorial optimisation problems are ubiquitous in artificial
intelli...
Automated persuasion systems (APS) aim to persuade a user to believe
som...
We are concerned with debugging concept-based gray-box models (GBMs). Th...
Mixed-integer linear programs (MILPs) are widely used in artificial
inte...
We tackle sequential learning under label noise in applications where a ...
We propose Nester, a method for injecting neural networks into constrain...
We introduce and study knowledge drift (KD), a complex form of drift tha...
Circuit representations are becoming the lingua franca to express and re...
We introduce Explearn, an online algorithm that learns to jointly output...
Applications like personal assistants need to be aware ofthe user's cont...
The ability to learn from human supervision is fundamental for personal
...
We introduce explanatory guided learning (XGL), a novel interactive lear...
Generative Adversarial Networks (GANs) struggle to generate structured
o...
Recent work has demonstrated the promise of combining local explanations...
Everybody wants to analyse their data, but only few posses the data scie...
Deep neural networks have shown excellent performances in many real-worl...
Arguments in favor of injecting symbolic knowledge into neural architect...
Many problems in operations research require that constraints be specifi...
Although interactive learning puts the user into the loop, the learner
r...
We tackle the problem of constructive preference elicitation, that is th...
Peference elicitation is the task of suggesting a highly preferred
confi...
When faced with complex choices, users refine their own preference crite...
In this paper we propose an approach to preference elicitation that is
s...
Modelling problems containing a mixture of Boolean and numerical variabl...
Generally speaking, the goal of constructive learning could be seen as, ...