Modeling Decisions for Artificial Intelligence
21st International Conference, MDAI 2024, Tokyo, Japan, August 27–31, 2024, Proceedings
Page
%P
-
Article
Open AccessPreprocessed Spectral Clustering with Higher Connectivity for Robustness in Real-World Applications
This paper introduces a novel model for spectral clustering to solve the problem of poor connectivity among points within the same cluster as this can negatively impact the performance of spectral clustering. ...
-
Article
Open AccessExplainable machine learning models with privacy
The importance of explainable machine learning models is increasing because users want to understand the reasons behind decisions in data-driven models. Interpretability and explainability emerge from this nee...
-
Chapter and Conference Paper
Attribute Disclosure Risk in Smart Meter Data
This paper studies attribute disclosure risk in aggregated smart meter data. Smart meter data is commonly aggregated to preserve the privacy of individual contributions. The published data shows aggregated con...
-
Chapter and Conference Paper
Integrally Private Model Selection for Support Vector Machine
Today, there are unlimited applications of data mining techniques. According to ongoing privacy regulations, data mining techniques that preserve users’ privacy are a primary requirement. Our work contributes ...
-
Chapter and Conference Paper
The Past and Future of Fuzzy Measures and Fuzzy Integrals
This paper recognizes and summarizes the main contributions of Prof. Michio Sugeno in the area of fuzzy measures and integrals. A concept he introduced in his PhD dissertation in 1974.
-
Chapter and Conference Paper
Empirical Evaluation of Synthetic Data Created by Generative Models via Attribute Inference Attack
The disclosure risk of synthetic/artificial data is still being determined. Studies show that synthetic data generation techniques generate similar data to the original data and sometimes even the exact origin...
-
Chapter and Conference Paper
Games, Fuzzy Measures, Indices, and Explainable ML: Exploiting the Game
The Shapley value is currently used for explainability of machine learning models. It allows to evaluate the contribution of a variable into the final output. For this, a game (in the sense of game theory) nee...
-
Chapter and Conference Paper
Differentially Private Traffic Flow Prediction Using Transformers: A Federated Approach
Accurate traffic flow prediction plays an important role in intelligent transportation management and reducing traffic congestion for smart cities. Existing traffic flow prediction techniques using deep learni...
-
Chapter and Conference Paper
DISCOLEAF: Personalized DIScretization of COntinuous Attributes for LEArning with Federated Decision Trees
Federated learning is a distributed machine learning framework, in which each client participating to the federation trains a machine learning model on its data, and shares the trained model information with a...
-
Chapter and Conference Paper
Can Synthetic Data Preserve Manifold Properties?
Machine learning has shown remarkable performance in modeling large datasets with complex patterns. As the amount of data increases, it often leads to high-dimensional feature spaces. This data may contain con...
-
Book and Conference Proceedings
-
Chapter and Conference Paper
Task-Specific Knowledge Distillation with Differential Privacy in LLMs
Large Language Models (LLMs) have demonstrated state-of-the-art performance across various applications. However, these models which consists of millions of parameters still face challenges due to their comput...
-
Article
Open AccessAttribute disclosure risk for k-anonymity: the case of numerical data
k-Anonymity is one of the most well-known privacy models. Internal and external attacks were discussed for this privacy model, both focusing on categorical data. These attacks can be seen as attribute disclosur.....
-
Article
Special issue on data mining and data privacy
This special issue encompasses fourteen papers that focus on different aspects related to data science. This ranges from supervised and unsupervised machine learning algorithms to extract knowledge from data, ...
-
Article
Open AccessRounding based continuous data discretization for statistical disclosure control
“Rounding” can be understood as a way to coarsen continuous data. That is, low level and infrequent values are replaced by high-level and more frequent representative values. This concept is explored as a meth...
-
Article
Data anonymization with imprecise rules and its performance evaluations
Privacy protection is absolutely imperative for data releases when the utilization of public data and big data is getting popular. In this paper, data anonymization methods using rough set-based rule induction...
-
Article
Open AccessLiterature Review of the Recent Trends and Applications in Various Fuzzy Rule-Based Systems
Fuzzy rule-based systems (FRBSs) is a rule-based system which uses linguistic fuzzy variables as antecedents and consequent to represent human-understandable knowledge. They have been applied to various applic...
-
Article
Open AccessA systematic construction of non-i.i.d. data sets from a single data set: non-identically distributed data
Data-driven models strongly depend on data. Nevertheless, for research and academic purposes, public data sets are usually considered and analyzed. For example, most machine learning algorithms are applied and...
-
Chapter and Conference Paper
Optimal Transport and the Wasserstein Distance for Fuzzy Measures: An Example
Probabilities and, in general, additive measures are extensively used in all kind of applications. A key concept in mathematics is the one of a distance. Different distances provide different implementations o...
-
Chapter and Conference Paper
Data Reconstruction Attack Against Principal Component Analysis
Attacking machine learning models is one of the many ways to measure the privacy of machine learning models. Therefore, studying the performance of attacks against machine learning techniques is essential to k...
