Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Mateja Jamnik

Mateja Jamnik

Towards Robust Metrics for Concept Representation Evaluation

Jan 25, 2023
Mateo Espinosa Zarlenga, Pietro Barbiero, Zohreh Shams, Dmitry Kazhdan, Umang Bhatt, Adrian Weller, Mateja Jamnik

Figure 1 for Towards Robust Metrics for Concept Representation Evaluation

Figure 2 for Towards Robust Metrics for Concept Representation Evaluation

Figure 3 for Towards Robust Metrics for Concept Representation Evaluation

Figure 4 for Towards Robust Metrics for Concept Representation Evaluation

* To appear at AAAI 2023

Access Paper or Ask Questions

Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data

Nov 28, 2022
Andrei Margeloiu, Nikola Simidjievski, Pietro Lio, Mateja Jamnik

Figure 1 for Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data

Figure 2 for Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data

Figure 3 for Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data

Figure 4 for Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data

* Accepted to AAAI-2023

Access Paper or Ask Questions

Explainer Divergence Scores (EDS): Some Post-Hoc Explanations May be Effective for Detecting Unknown Spurious Correlations

Nov 14, 2022
Shea Cardozo, Gabriel Islas Montero, Dmitry Kazhdan, Botty Dimanov, Maleakhi Wijaya, Mateja Jamnik, Pietro Lio

Figure 1 for Explainer Divergence Scores (EDS): Some Post-Hoc Explanations May be Effective for Detecting Unknown Spurious Correlations

Figure 2 for Explainer Divergence Scores (EDS): Some Post-Hoc Explanations May be Effective for Detecting Unknown Spurious Correlations

Figure 3 for Explainer Divergence Scores (EDS): Some Post-Hoc Explanations May be Effective for Detecting Unknown Spurious Correlations

Figure 4 for Explainer Divergence Scores (EDS): Some Post-Hoc Explanations May be Effective for Detecting Unknown Spurious Correlations

* Presented at the AIMLAI workshop at the 31st ACM International Conference on Information and Knowledge Management (CIKM 2022)

Access Paper or Ask Questions

Graph-Conditioned MLP for High-Dimensional Tabular Biomedical Data

Nov 11, 2022
Andrei Margeloiu, Nikola Simidjievski, Pietro Lio', Mateja Jamnik

Figure 1 for Graph-Conditioned MLP for High-Dimensional Tabular Biomedical Data

Figure 2 for Graph-Conditioned MLP for High-Dimensional Tabular Biomedical Data

Figure 3 for Graph-Conditioned MLP for High-Dimensional Tabular Biomedical Data

* Presented at the 17th Machine Learning in Computational Biology (MLCB) meeting, 2022

Access Paper or Ask Questions

Distributed representations of graphs for drug pair scoring

Sep 19, 2022
Paul Scherer, Pietro Liò, Mateja Jamnik

Figure 1 for Distributed representations of graphs for drug pair scoring

Figure 2 for Distributed representations of graphs for drug pair scoring

Figure 3 for Distributed representations of graphs for drug pair scoring

Figure 4 for Distributed representations of graphs for drug pair scoring

* 9 main pages, 6 pages reference and appendix

Access Paper or Ask Questions

Concept Embedding Models

Sep 19, 2022
Mateo Espinosa Zarlenga, Pietro Barbiero, Gabriele Ciravegna, Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti, Zohreh Shams, Frederic Precioso, Stefano Melacci, Adrian Weller, Pietro Lio, Mateja Jamnik

Figure 1 for Concept Embedding Models

Figure 2 for Concept Embedding Models

Figure 3 for Concept Embedding Models

Figure 4 for Concept Embedding Models

* To appear at NeurIPS 2022

Access Paper or Ask Questions

Representational Systems Theory: A Unified Approach to Encoding, Analysing and Transforming Representations

Jun 07, 2022
Daniel Raggi, Gem Stapleton, Mateja Jamnik, Aaron Stockdill, Grecia Garcia Garcia, Peter C-H. Cheng

* 118 pages total: 94 of main paper + 2 of references + 22 of appendices. Submitted to JACM. Authors Gem Stapleton and Daniel Raggi contributed equally to this research

Access Paper or Ask Questions