37 items found

Filter Results
  • ConferencePaper

    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...
    • The resource: 'Link to Publication' is not accessible as guest user. You must login to access it!
  • JournalArticle

    Temporal social network reconstruction using wireless proximity sensors: mode...

    The emerging technologies of wearable wireless devices open entirely new ways to record various aspects of human social interactions in a broad range of settings. Such...
    • The resource: 'Link to Publication' is not accessible as guest user. You must login to access it!
  • ConferencePaper

    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...
    • bibtex
      The resource: 'BibTeX file' is not accessible as guest user. You must login to access it!
    • PDF
      The resource: 'Conference Paper' is not accessible as guest user. You must login to access it!
  • JournalArticle

    Fairer machine learning in the real world

    Mitigating discrimination without collecting sensitive data Decisions based on algorithmic, machine learning models can be unfair, reproducing biases in historical data used...
    • bibtex
      The resource: 'BibTeX' is not accessible as guest user. You must login to access it!
    • PDF
      The resource: 'Journal Article' is not accessible as guest user. You must login to access it!
  • JournalArticle

    Fair Transparent and Accountable Algorithmic Decision making Processes

    The Premise, the Proposed Solutions, and the Open Challenges The combination of increased availability of large amounts of fine-grained human behavioral data and advances in...
    • bibtex
      The resource: 'BibTeX' is not accessible as guest user. You must login to access it!
    • HTML
      The resource: 'Journal Article' is not accessible as guest user. You must login to access it!
  • ConferencePaper

    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...
    • bibtex
      The resource: 'BibTeX' is not accessible as guest user. You must login to access it!
    • PDF
      The resource: 'Conference Proceeding ...' is not accessible as guest user. You must login to access it!
  • ConferencePaper

    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...
    • bibtex
      The resource: 'BibTeX' is not accessible as guest user. You must login to access it!
    • HTML
      The resource: 'Conference Proceedings' is not accessible as guest user. You must login to access it!
  • JournalArticle

    Fair Prediction with Disparate Impact A Study of Bias in Recidivism Predictio...

    Recidivism prediction instruments (RPIs) provide decision-makers with an assessment of the likelihood that a criminal defendant will reoffend at a future point in time....
    • bibtex
      The resource: 'BibTeX file' is not accessible as guest user. You must login to access it!
    • HTML
      The resource: 'Journal Article' is not accessible as guest user. You must login to access it!
  • Access required...

    ×

    ConferencePaper

    Private 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...
  • Access required...

    ×

    ConferencePaper

    Private 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...
  • JournalArticle

    GLocalX-From Local to Global Explanations of Black Box AI Models

    Artificial Intelligence (AI) has come to prominence as one of the major components of our society, with applications in most aspects of our lives. In this field, complex and...
    • The resource: 'Link to Publication' is not accessible as guest user. You must login to access it!
  • JournalArticle

    Toward Accountable Discrimination Aware Data Mining

    "Big Data" and data-mined inferences are affecting more and more of our lives, and concerns about their possible discriminatory effects are growing. Methods for...
    • HTML
      The resource: 'html' is not accessible as guest user. You must login to access it!
    • BibTeX
      The resource: 'BibTeX' is not accessible as guest user. You must login to access it!
  • JournalArticle

    Solving the Black Box Problem. A Normative Framework for Explainable Artifici...

    Many of the computing systems programmed using Machine Learning are opaque: it is difficult to know why they do what they do or how they work. Explainable Artificial...
    • BibTeX
      The resource: 'BibTeX' is not accessible as guest user. You must login to access it!
    • HTML
      The resource: 'html' is not accessible as guest user. You must login to access it!
  • JournalArticle

    Seeing without knowing. Limitations of transparency and its application to al...

    Models for understanding and holding systems accountable have long rested upon ideals and logics of transparency. Being able to see a system is sometimes equated with being able...
    • BibTeX
      The resource: 'BibTeX' is not accessible as guest user. You must login to access it!
    • HTML
      The resource: 'html' is not accessible as guest user. You must login to access it!
  • JournalArticle

    The PGM-index a fully-dynamic compressed learned index with provable worst-ca...

    We present the first learned index that supports predecessor, range queries and updates within provably efficient time and space bounds in the worst case. In the (static)...
    • PDF
      The resource: 'link to publication' is not accessible as guest user. You must login to access it!
  • Access required...

    ×

    ConferencePaper

    Private 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...
  • ConferencePaper

    Explanation of Deep Models with Limited Interaction for Trade Secret and Priv...

    An ever-increasing number of decisions affecting our lives are made by algorithms. For this reason, algorithmic transparency is becoming a pressing need: automated decisions...
    • BibTeX
      The resource: 'BibTeX' is not accessible as guest user. You must login to access it!
    • HTML
      The resource: 'html' is not accessible as guest user. You must login to access it!
  • ConferencePaper

    Multi layered Explanations from Algorithmic Impact Assessments in the GDPR

    Impact assessments have received particular attention on both sides of the Atlantic as a tool for implementing algorithmic accountability. The aim of this paper is to address...
    • BibTeX
      The resource: 'BibTeX' is not accessible as guest user. You must login to access it!
    • HTML
      The resource: 'html' is not accessible as guest user. You must login to access it!
  • JournalArticle

    Modeling Adversarial Behavior Against Mobility Data Privacy

    Privacy risk assessment is a crucial issue in any privacy-aware analysis process. Traditional frameworks for privacy risk assessment systematically generate the assumed...
    • The resource: 'Link to Publication' is not accessible as guest user. You must login to access it!
  • JournalArticle

    Explanation in artificial intelligence. Insights from the social sciences

    There has been a recent resurgence in the area of explainable artificial intelligence as researchers and practitioners seek to provide more transparency to their algorithms....
    • HTML
      The resource: 'html' is not accessible as guest user. You must login to access it!
    • BibTeX
      The resource: 'BibTeX' is not accessible as guest user. You must login to access it!