Mateo Espinosa Zarlenga

35 papers A* 9C 2Journal 21Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
Actionable Interpretability Must Be Defined in Terms of Symmetries.
CoRR
Pietro Barbiero, Mateo Espinosa Zarlenga, Francesco Giannini, Alberto Termine, Filippo Bonchi, Mateja Jamnik, Giuseppe Marra
2026 J jnl
Digging Deeper: Learning Multi-Level Concept Hierarchies.
CoRR
Oscar Hill, Mateo Espinosa Zarlenga, Mateja Jamnik
2026 J jnl
Hierarchical Concept-based Interpretable Models.
CoRR
Oscar Hill, Mateo Espinosa Zarlenga, Mateja Jamnik
2026 J jnl
Mixture of Concept Bottleneck Experts.
CoRR
Francesco De Santis, Gabriele Ciravegna, Giovanni de Felice, Arianna Casanova, Francesco Giannini, Michelangelo Diligenti, Mateo Espinosa Zarlenga, Pietro Barbiero, Johannes Schneider, Danilo Giordano
2025 A* conf
Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization.
ICML
Emiliano Penaloza, Tianyue H. Zhang, Laurent Charlin, Mateo Espinosa Zarlenga
2025 J jnl
Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization.
CoRR
Emiliano Penaloza, Tianyue H. Zhang, Laurent Charlin, Mateo Espinosa Zarlenga
2025 A* conf
Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts.
ICML
Mateo Espinosa Zarlenga, Gabriele Dominici, Pietro Barbiero, Zohreh Shams, Mateja Jamnik
2025 J jnl
Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts.
CoRR
Mateo Espinosa Zarlenga, Gabriele Dominici, Pietro Barbiero, Zohreh Shams, Mateja Jamnik
2025 A* conf
Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning.
ICLR
Gabriele Dominici, Pietro Barbiero, Mateo Espinosa Zarlenga, Alberto Termine, Martin Gjoreski, Giuseppe Marra, Marc Langheinrich
2025 J jnl
Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts.
CoRR
Andrea Pugnana, Riccardo Massidda, Francesco Giannini, Pietro Barbiero, Mateo Espinosa Zarlenga, Roberto Pellungrini, Gabriele Dominici, Fosca Giannotti, Davide Bacciu
2025 J jnl
Do Concept Bottleneck Models Respect Localities?
Trans. Mach. Learn. Res.
Naveen Janaki Raman, Mateo Espinosa Zarlenga, Juyeon Heo, Mateja Jamnik
2025 J jnl
Foundations of Interpretable Models.
CoRR
Pietro Barbiero, Mateo Espinosa Zarlenga, Alberto Termine, Mateja Jamnik, Giuseppe Marra
2025 J jnl
Neural Interpretable Reasoning.
CoRR
Pietro Barbiero, Giuseppe Marra, Gabriele Ciravegna, David Debot, Francesco De Santis, Michelangelo Diligenti, Mateo Espinosa Zarlenga, Francesco Giannini
2024 J jnl
Causal Concept Embedding Models: Beyond Causal Opacity in Deep Learning.
CoRR
Gabriele Dominici, Pietro Barbiero, Mateo Espinosa Zarlenga, Alberto Termine, Martin Gjoreski, Giuseppe Marra, Marc Langheinrich
2024 J jnl
Do Concept Bottleneck Models Obey Locality?
CoRR
Naveen Raman, Mateo Espinosa Zarlenga, Juyeon Heo, Mateja Jamnik
2024 — conf
Efficient Bias Mitigation Without Privileged Information.
ECCV (72)
Mateo Espinosa Zarlenga, Swami Sankaranarayanan, Jerone T. A. Andrews, Zohreh Shams, Mateja Jamnik, Alice Xiang
2024 J jnl
Efficient Bias Mitigation Without Privileged Information.
CoRR
Mateo Espinosa Zarlenga, Swami Sankaranarayanan, Jerone T. A. Andrews, Zohreh Shams, Mateja Jamnik, Alice Xiang
2024 — conf
From Must to May: Enabling Test-Time Feature Imputation and Interventions.
HI-AI@KDD
Evan Rex, Mateo Espinosa Zarlenga, Andrei Margeloiu, Mateja Jamnik
2024 — ed.
Proceedings of the KDD Workshop on Human-Interpretable AI 2024 co-located with 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2024), Centre de Convencions Internacional de Barcelona, Spain, August 26, 2024.
HI-AI@KDD
Gabriele Ciravegna, Mateo Espinosa Zarlenga, Pietro Barbiero, Zohreh Shams, Francesco Giannini, Damien Garreau, Mateja Jamnik, Tania Cerquitelli
2024 A* conf
Understanding Inter-Concept Relationships in Concept-Based Models.
ICML
Naveen Raman, Mateo Espinosa Zarlenga, Mateja Jamnik
2024 J jnl
Understanding Inter-Concept Relationships in Concept-Based Models.
CoRR
Naveen Raman, Mateo Espinosa Zarlenga, Mateja Jamnik
2024 A* conf
Workshop on Human-Interpretable AI.
KDD
Gabriele Ciravegna, Mateo Espinosa Zarlenga, Pietro Barbiero, Francesco Giannini, Zohreh Shams, Damien Garreau, Mateja Jamnik, Tania Cerquitelli
2023 C conf
Human Uncertainty in Concept-Based AI Systems.
AIES
Katherine Maeve Collins, Matthew Barker, Mateo Espinosa Zarlenga, Naveen Raman, Umang Bhatt, Mateja Jamnik, Ilia Sucholutsky, Adrian Weller, Krishnamurthy Dvijotham
2023 J jnl
Human Uncertainty in Concept-Based AI Systems.
CoRR
Katherine M. Collins, Matthew Barker, Mateo Espinosa Zarlenga, Naveen Raman, Umang Bhatt, Mateja Jamnik, Ilia Sucholutsky, Adrian Weller, Krishnamurthy Dvijotham
2023 A* conf
Interpretable Neural-Symbolic Concept Reasoning.
ICML
Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini, Mateo Espinosa Zarlenga, Lucie Charlotte Magister, Alberto Tonda, Pietro Lio, Frédéric Precioso, Mateja Jamnik, Giuseppe Marra
2023 C conf
Interpretable Neural-Symbolic Concept Reasoning.
NeSy
Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini, Mateo Espinosa Zarlenga, Lucie Charlotte Magister, Alberto Tonda, Pietro Liò, Frédéric Precioso, Mateja Jamnik, Giuseppe Marra
2023 J jnl
Interpretable Neural-Symbolic Concept Reasoning.
CoRR
Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini, Mateo Espinosa Zarlenga, Lucie Charlotte Magister, Alberto Tonda, Pietro Lio', Frédéric Precioso, Mateja Jamnik, Giuseppe Marra
2023 A* conf
Learning to Receive Help: Intervention-Aware Concept Embedding Models.
NeurIPS
Mateo Espinosa Zarlenga, Katie Collins, Krishnamurthy Dvijotham, Adrian Weller, Zohreh Shams, Mateja Jamnik
2023 J jnl
Learning to Receive Help: Intervention-Aware Concept Embedding Models.
CoRR
Mateo Espinosa Zarlenga, Katherine M. Collins, Krishnamurthy Dvijotham, Adrian Weller, Zohreh Shams, Mateja Jamnik
2023 J jnl
TabCBM: Concept-based Interpretable Neural Networks for Tabular Data.
Trans. Mach. Learn. Res.
Mateo Espinosa Zarlenga, Zohreh Shams, Michael E. Nelson, Been Kim, Mateja Jamnik
2023 A* conf
Towards Robust Metrics for Concept Representation Evaluation.
AAAI
Mateo Espinosa Zarlenga, Pietro Barbiero, Zohreh Shams, Dmitry Kazhdan, Umang Bhatt, Adrian Weller, Mateja Jamnik
2023 J jnl
Towards Robust Metrics for Concept Representation Evaluation.
CoRR
Mateo Espinosa Zarlenga, Pietro Barbiero, Zohreh Shams, Dmitry Kazhdan, Umang Bhatt, Adrian Weller, Mateja Jamnik
2022 J jnl
Concept Embedding Models.
CoRR
Mateo Espinosa Zarlenga, Pietro Barbiero, Gabriele Ciravegna, Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti, Zohreh Shams, Frédéric Precioso, Stefano Melacci, Adrian Weller, Pietro Liò, Mateja Jamnik
2022 A* conf
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off.
NeurIPS
Mateo Espinosa Zarlenga, Pietro Barbiero, Gabriele Ciravegna, Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti, Zohreh Shams, Frédéric Precioso, Stefano Melacci, Adrian Weller, Pietro Lió, Mateja Jamnik
2021 J jnl
Efficient Decompositional Rule Extraction for Deep Neural Networks.
CoRR
Mateo Espinosa Zarlenga, Zohreh Shams, Mateja Jamnik