Search Results for author:
Found 37 papers, 25 papers with code
Logic Explanation of AI Classifiers by Categorical Explaining Functors
The most common methods in explainable artificial intelligence are post-hoc techniques which identify the most relevant features used by pretrained opaque models.
Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts
However, when intervened on, CBMs assume the availability of humans that can identify the need to intervene and always provide correct interventions.
Neural Interpretable Reasoning
We formalize a novel modeling framework for achieving interpretability in deep learning, anchored in the principle of inference equivariance.
A Survey on Federated Learning in Human Sensing
However, its reliance on detailed and often privacy-sensitive data as the basis for its machine learning (ML) models raises significant legal and ethical concerns.
Counterfactual Explanations for Clustering Models
While many explainable artificial intelligence techniques exist for supervised machine learning, unsupervised learning -- and clustering in particular -- has been largely neglected.
Interpretable Concept-Based Memory Reasoning
The presence of an explicit memory and the symbolic evaluation allow domain experts to inspect and formally verify the validity of certain global properties of interest for the task prediction process.
Self-supervised Interpretable Concept-based Models for Text Classification
Additionally, we show that our models are (i) interpretable, offering meaningful logical explanations for their predictions; (ii) interactable, allowing humans to modify intermediate predictions through concept interventions; and (iii) controllable, guiding the LLMs' decoding process to follow a required decision-making path.
Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning
Causal opacity denotes the difficulty in understanding the "hidden" causal structure underlying the decisions of deep neural network (DNN) models.
AnyCBMs: How to Turn Any Black Box into a Concept Bottleneck Model
Interpretable deep learning aims at developing neural architectures whose decision-making processes could be understood by their users.
Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning
Federated Learning (FL), a privacy-aware approach in distributed deep learning environments, enables many clients to collaboratively train a model without sharing sensitive data, thereby reducing privacy risks.
Counterfactual Concept Bottleneck Models
Current deep learning models are not designed to simultaneously address three fundamental questions: predict class labels to solve a given classification task (the "What?
Digital Histopathology with Graph Neural Networks: Concepts and Explanations for Clinicians
To address the challenge of the ``black-box" nature of deep learning in medical settings, we combine GCExplainer - an automated concept discovery solution - along with Logic Explained Networks to provide global explanations for Graph Neural Networks.
Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Concepts
A line of interpretable methods approach this by discovering a small set of relevant concepts as subgraphs in the last GNN layer that together explain the prediction.
From Charts to Atlas: Merging Latent Spaces into One
Models trained on semantically related datasets and tasks exhibit comparable inter-sample relations within their latent spaces.
Relational Concept Bottleneck Models
The design of interpretable deep learning models working in relational domains poses an open challenge: interpretable deep learning methods, such as Concept Bottleneck Models (CBMs), are not designed to solve relational problems, while relational deep learning models, such as Graph Neural Networks (GNNs), are not as interpretable as CBMs.
SHARCS: Shared Concept Space for Explainable Multimodal Learning
Multimodal learning is an essential paradigm for addressing complex real-world problems, where individual data modalities are typically insufficient to accurately solve a given modelling task.
Categorical Foundations of Explainable AI: A Unifying Theory
Explainable AI (XAI) aims to address the human need for safe and reliable AI systems.
Interpretable Neural-Symbolic Concept Reasoning
Deep learning methods are highly accurate, yet their opaque decision process prevents them from earning full human trust.
GCI: A (G)raph (C)oncept (I)nterpretation Framework
Explainable AI (XAI) underwent a recent surge in research on concept extraction, focusing on extracting human-interpretable concepts from Deep Neural Networks.
Explainable Artificial Intelligence (XAI)
Molecular Property Prediction
+2
Towards Robust Metrics for Concept Representation Evaluation
In this paper, we show that such metrics are not appropriate for concept learning and propose novel metrics for evaluating the purity of concept representations in both approaches.
Extending Logic Explained Networks to Text Classification
Recently, Logic Explained Networks (LENs) have been proposed as explainable-by-design neural models providing logic explanations for their predictions.
Global Explainability of GNNs via Logic Combination of Learned Concepts
While instance-level explanation of GNN is a well-studied problem with plenty of approaches being developed, providing a global explanation for the behaviour of a GNN is much less explored, despite its potential in interpretability and debugging.
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off
Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy.
Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis
We propose a novel approach for producing global explanations for GNNs using neuron-level concepts to enable practitioners to have a high-level view of the model.
Encoding Concepts in Graph Neural Networks
The opaque reasoning of Graph Neural Networks induces a lack of human trust.
On The Quality Assurance Of Concept-Based Representations
Recent work on Explainable AI has focused on concept-based explanations, where deep learning models are explained in terms of high-level units of information, referred to as concepts.
Logic Explained Networks
The language used to communicate the explanations must be formal enough to be implementable in a machine and friendly enough to be understandable by a wide audience.
Algorithmic Concept-based Explainable Reasoning
Recent research on graph neural network (GNN) models successfully applied GNNs to classical graph algorithms and combinatorial optimisation problems.
Entropy-based Logic Explanations of Neural Networks
Explainable artificial intelligence has rapidly emerged since lawmakers have started requiring interpretable models for safety-critical domains.
Ranked #1 on
Image Classification
on CUB
Graph representation forecasting of patient's medical conditions: towards a digital twin
Objective: Modern medicine needs to shift from a wait and react, curative discipline to a preventative, interdisciplinary science aiming at providing personalised, systemic and precise treatment plans to patients.
Gradient-based Competitive Learning: Theory
The former is just an adaptation of a standard competitive layer for deep clustering, while the latter is trained on the transposed matrix.
Topological Gradient-based Competitive Learning
The aim of this work is to present a novel comprehensive theory aspiring at bridging competitive learning with gradient-based learning, thus allowing the use of extremely powerful deep neural networks for feature extraction and projection combined with the remarkable flexibility and expressiveness of competitive learning.
Modeling Generalization in Machine Learning: A Methodological and Computational Study
As machine learning becomes more and more available to the general public, theoretical questions are turning into pressing practical issues.
A Novel Outlook on Feature Selection as a Multi-objective Problem
We thus propose a multi-objective optimization approach to feature selection, EvoFS, with the objectives to i. minimize feature subset size, ii.
Uncovering Coresets for Classification With Multi-Objective Evolutionary Algorithms
A coreset is a subset of the training set, using which a machine learning algorithm obtains performances similar to what it would deliver if trained over the whole original data.
Ranked #1 on
Core set discovery
on MNIST
The GH-EXIN neural network for hierarchical clustering
Furthermore, an important and very promising application of GH-EXIN in two-way hierarchical clustering, for the analysis of gene expression data in the study of the colorectal cancer is described.
