Mirko Marras

Knowledge is Power, Understanding is Impact: Utility and Beyond Goals, Explanation Quality, and Fairness in Path Reasoning Recommendation

Jan 14, 2023
Giacomo Balloccu, Ludovico Boratto, Christian Cancedda, Gianni Fenu, Mirko Marras

Figure 1 for Knowledge is Power, Understanding is Impact: Utility and Beyond Goals, Explanation Quality, and Fairness in Path Reasoning Recommendation

Figure 2 for Knowledge is Power, Understanding is Impact: Utility and Beyond Goals, Explanation Quality, and Fairness in Path Reasoning Recommendation

Figure 3 for Knowledge is Power, Understanding is Impact: Utility and Beyond Goals, Explanation Quality, and Fairness in Path Reasoning Recommendation

Figure 4 for Knowledge is Power, Understanding is Impact: Utility and Beyond Goals, Explanation Quality, and Fairness in Path Reasoning Recommendation

* Accepted at the 45th European Conference on Information Retrieval (ECIR 2023)

Access Paper or Ask Questions

Trusting the Explainers: Teacher Validation of Explainable Artificial Intelligence for Course Design

Dec 26, 2022
Vinitra Swamy, Sijia Du, Mirko Marras, Tanja Käser

Figure 2 for Trusting the Explainers: Teacher Validation of Explainable Artificial Intelligence for Course Design

Figure 3 for Trusting the Explainers: Teacher Validation of Explainable Artificial Intelligence for Course Design

Figure 4 for Trusting the Explainers: Teacher Validation of Explainable Artificial Intelligence for Course Design

* Accepted as a full paper at LAK 2023: The 13th International Learning Analytics and Knowledge Conference, March 13-17, 2023, Arlington, Texas, USA

Access Paper or Ask Questions

Do Not Trust a Model Because It is Confident: Uncovering and Characterizing Unknown Unknowns to Student Success Predictors in Online-Based Learning

Dec 16, 2022
Roberta Galici, Tanja Käser, Gianni Fenu, Mirko Marras

Figure 1 for Do Not Trust a Model Because It is Confident: Uncovering and Characterizing Unknown Unknowns to Student Success Predictors in Online-Based Learning

Figure 2 for Do Not Trust a Model Because It is Confident: Uncovering and Characterizing Unknown Unknowns to Student Success Predictors in Online-Based Learning

Figure 3 for Do Not Trust a Model Because It is Confident: Uncovering and Characterizing Unknown Unknowns to Student Success Predictors in Online-Based Learning

Figure 4 for Do Not Trust a Model Because It is Confident: Uncovering and Characterizing Unknown Unknowns to Student Success Predictors in Online-Based Learning

* Accepted as a full paper at the International Conference on Learning Analytics & Knowledge (LAK23)

Access Paper or Ask Questions

Ripple: Concept-Based Interpretation for Raw Time Series Models in Education

Dec 13, 2022
Mohammad Asadi, Vinitra Swamy, Jibril Frej, Julien Vignoud, Mirko Marras, Tanja Käser

Figure 2 for Ripple: Concept-Based Interpretation for Raw Time Series Models in Education

Figure 3 for Ripple: Concept-Based Interpretation for Raw Time Series Models in Education

Figure 4 for Ripple: Concept-Based Interpretation for Raw Time Series Models in Education

* Accepted as a full paper at AAAI 2023: 37th AAAI Conference on Artificial Intelligence (EAAI: AI for Education Special Track), 7-14 of February 2023, Washington DC, USA

Access Paper or Ask Questions

The More Secure, The Less Equally Usable: Gender and Ethnicity (Un)fairness of Deep Face Recognition along Security Thresholds

Sep 30, 2022
Andrea Atzori, Gianni Fenu, Mirko Marras

Figure 2 for The More Secure, The Less Equally Usable: Gender and Ethnicity (Un)fairness of Deep Face Recognition along Security Thresholds

Figure 3 for The More Secure, The Less Equally Usable: Gender and Ethnicity (Un)fairness of Deep Face Recognition along Security Thresholds

* Accepted as a full paper at the 2nd International Workshop on Artificial Intelligence Methods for Smart Cities (AISC 2022)

Access Paper or Ask Questions

Reinforcement Recommendation Reasoning through Knowledge Graphs for Explanation Path Quality

Sep 11, 2022
Giacomo Balloccu, Ludovico Boratto, Gianni Fenu, Mirko Marras

Figure 2 for Reinforcement Recommendation Reasoning through Knowledge Graphs for Explanation Path Quality

Figure 3 for Reinforcement Recommendation Reasoning through Knowledge Graphs for Explanation Path Quality

Figure 4 for Reinforcement Recommendation Reasoning through Knowledge Graphs for Explanation Path Quality

* Manuscript and supplement, currently under review. arXiv admin note: text overlap with arXiv:2204.11241

Access Paper or Ask Questions

Explaining Bias in Deep Face Recognition via Image Characteristics

Aug 23, 2022
Andrea Atzori, Gianni Fenu, Mirko Marras

Figure 2 for Explaining Bias in Deep Face Recognition via Image Characteristics

Figure 3 for Explaining Bias in Deep Face Recognition via Image Characteristics

Figure 4 for Explaining Bias in Deep Face Recognition via Image Characteristics

* Accepted as a full paper at IJCB 2022: 2022 International Joint Conference on Biometrics

Access Paper or Ask Questions