-
Predicting and Explaining Privacy Risk Exposure in Mobility Data
Mobility data is a proxy of different social dynamics and its analysis enables a wide range of user services. Unfortunately, mobility data are very sensitive because the... -
Explaining Any Time Series Classifier
We present a method to explain the decisions of black box models for time series classification. The explanation consists of factual and counterfactual shapelet-based rules...-
HTML
The resource: 'Link to Publication' is not accessible as guest user. You must login to access it!
-
HTML
-
Interpretable Next Basket Prediction Boosted with Representative Recipes
Food is an essential element of our lives, cultures, and a crucial part of human experience. The study of food purchases can drive the design of practical services such as...-
HTML
The resource: 'Link to Publication' is not accessible as guest user. You must login to access it!
-
HTML
-
Beyond Distributive Fairness in Algorithmic Decision Making
Beyond Distributive Fairness in Algorithmic Decision Making Feature Selection for Procedurally Fair Learning With widespread use of machine learning methods in numerous... -
Private traits and attributes are predictable from digital records of human b...
We show that easily accessible digital records of behavior, Facebook Likes, can be used to automatically and accurately predict a range of highly sensitive personal attributes... -
Heterogeneous Document Embeddings for Cross-Lingual Text Classification
Funnelling (Fun) is a method for cross-lingual text classification (CLC) based on a two-tier ensemble for heterogeneous transfer learning. In Fun, 1st-tier classifiers, each...-
HTML
The resource: 'Link to Publication' is not accessible as guest user. You must login to access it!
-
HTML
-
A comparative study of fairness enhancing interventions in machine learning
Computers are increasingly used to make decisions that have significant impact on people's lives. Often, these predictions can affect different population subgroups... -
Focus Metric
https://github.com/HPAI-BSC/Focus-Metric Implementation of the Focus metric. This metric is able to evaluate explainability methods and quantify their coherency to the task...-
github
The resource: 'Focus Metric repository' is not accessible as guest user. You must login to access it!
-
github
-
Visualizing the Results of Boolean Matrix Factorizations
We provide a method to visualize the results of Boolean Matrix Factorization algorithms. Our method can also be used to visualize overlapping clusters in bipartite graphs. The... -
GLocalX - Explaining in a Local to Global setting
GLocalX is a model-agnostic Local to Global explanation algorithm. Given a set of local explanations expressed in the form of decision rules, and a black-box model to explain,... -
XAI Method for explaining time-series
LASTS is a framework that can explain the decisions of black box models for time series classification. The explanation consists of factual and counterfactual rules revealing... -
LORE
The recent years have witnessed the rise of accurate but obscure decision systems which hide the logic of their internal decision processes to the users. The lack of...-
python
The resource: 'LORE code' is not accessible as guest user. You must login to access it!
-
python
-
MARLENA
MARLENA is novel technique able to explain the reasons behind any black-box multi-label classifier decision. It will generate an explanation in the form of a decision rule....-
python
The resource: 'Marlena code' is not accessible as guest user. You must login to access it!
-
python
-
TriplEx - Explaining with Triples
TRIPLEX is an explainability package for Transformer-based models fine-tuned on Natural Language Inference, Semantic Text Similarity, or Text Classification tasks. TRIPLEX... -
Reducing Graph Structural Bias by Adding shortcut edges
Algorithms that tackle the problem of minimizing average/maximum hitting time (BMAH/BMMH) between different social network groups, given fixed shortcut edges. The...-
Data
The resource: 'Social network dataset' is not accessible as guest user. You must login to access it!
-
Data
-
Geolet
Geolet is a Python library that offers an interpretable transformation and classification approach for trajectory data. Geolet first partitions trajectories into multiple... -
Visualizing the Results of Biclustering and Boolean Matrix Factorization Algo...
This archive contains the code to visualize biclusters from the paper "Visualizing Overlapping Biclusterings and Boolean Matrix Factorizations" by Thibault Marette, Pauli... -
Interaction bias. Experiments dataset
Artificial Intelligence (AI) is increasingly used to build Decision Support Systems (DSS) across many domains. In our work, we conducted a series of experiments designed to...-
JSON
The resource: 'Dataset' is not accessible as guest user. You must login to access it!
-
JSON
-
Machine Learning Explainability Through Comprehensible Decision Trees
The role of decisions made by machine learning algorithms in our lives is ever increasing. In reaction to this phenomenon, the European General Data Protection Regulation...
