A comparison of instance-level counterfactual explanation algorithms for behavioral and textual data: SEDC, LIME-C and SHAP-C
Predictive systems based on high-dimensional behavioral and textual data have serious
comprehensibility and transparency issues: linear models require investigating thousands of …
comprehensibility and transparency issues: linear models require investigating thousands of …
RSS++ load and state-aware receive side scaling
While the current literature typically focuses on load-balancing among multiple servers, in
this paper, we demonstrate the importance of load-balancing within a single machine …
this paper, we demonstrate the importance of load-balancing within a single machine …
Explaining data-driven decisions made by AI systems: the counterfactual approach
We examine counterfactual explanations for explaining the decisions made by model-based
AI systems. The counterfactual approach we consider defines an explanation as a set of the …
AI systems. The counterfactual approach we consider defines an explanation as a set of the …
Tractability of explaining classifier decisions
MC Cooper, J Marques-Silva - Artificial Intelligence, 2023 - Elsevier
Explaining decisions is at the heart of explainable AI. We investigate the computational
complexity of providing a formally-correct and minimal explanation of a decision taken by a …
complexity of providing a formally-correct and minimal explanation of a decision taken by a …
On the tractability of explaining decisions of classifiers
MC Cooper, J Marques-Silva - 27th International Conference on …, 2021 - drops.dagstuhl.de
Explaining decisions is at the heart of explainable AI. We investigate the computational
complexity of providing a formally-correct and minimal explanation of a decision taken by a …
complexity of providing a formally-correct and minimal explanation of a decision taken by a …
Optical experimental solution for the multiway number partitioning problem and its application to computing power scheduling
J Wen, Z Wang, Z Huang, D Cai, B Jia, C Cao… - Science China Physics …, 2023 - Springer
Quantum computing is an emerging technology that is expected to realize an exponential
increase in computing power. Recently, its theoretical foundation and application scenarios …
increase in computing power. Recently, its theoretical foundation and application scenarios …
[PDF][PDF] Explaining data-driven decisions made by AI systems: the counterfactual approach
Lack of understanding of the decisions made by model-based AI systems is one of the main
barriers for their adoption. We examine counterfactual explanations, which are becoming an …
barriers for their adoption. We examine counterfactual explanations, which are becoming an …
Demand-aware network design with minimal congestion and route lengths
Emerging communication technologies allow to reconfigure the physical network topology at
runtime, enabling demand-aware networks (DANs): networks whose topology is optimized …
runtime, enabling demand-aware networks (DANs): networks whose topology is optimized …
Evolving objective function for improved variational quantum optimization
I Kolotouros, P Wallden - Physical Review Research, 2022 - APS
A promising approach to useful computational quantum advantage is to use variational
quantum algorithms for optimization problems. Crucial for the performance of these …
quantum algorithms for optimization problems. Crucial for the performance of these …
Envy-free matchings in bipartite graphs and their applications to fair division
E Aigner-Horev, E Segal-Halevi - Information Sciences, 2022 - Elsevier
A matching in a bipartite graph with parts X and Y is called envy-free, if no unmatched vertex
in X is a adjacent to a matched vertex in Y. Every perfect matching is envy-free, but envy-free …
in X is a adjacent to a matched vertex in Y. Every perfect matching is envy-free, but envy-free …