A Reproducibility Study of Deep and Surface Machine Learning Methods for Human-related Trajectory Prediction

Prenkaj, Bardh; Velardi, Paola; Distante, Damiano; Faralli, Stefano

doi:10.1145/3340531.3412088

“…On the other end of the spectrum of explainability, we find inherently interpretable white-box prediction models (Loyola-González 2019), which are preferred for decisionmaking purposes (Verenich et al 2019). Alas, black-box models demonstrate superior performance and generalisation capabilities when dealing with high-dimensional data (Aragona et al 2021;Ding et al 2019;Feng, Tang, and Liu 2019;Huang et al 2020;Madeddu, Stilo, and Velardi 2020;Prenkaj et al 2021Prenkaj et al , 2020Prenkaj et al , 2023aVerma, Mandal, and Gupta 2022;Wang, Yu, and Miao 2017).…”

Section: Introductionmentioning

confidence: 95%

Developing and Evaluating Graph Counterfactual Explanation with GRETEL

Prado-Romero

¹

,

Prenkaj

²

,

Stilo

³

2023

Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Counterfactual Explanation (CE) techniques have garnered attention as a means to provide insights to the users engaging with AI systems. While extensively researched in domains such as medical imaging and autonomous vehicles, Graph Counterfactual Explanation (GCE) methods have been comparatively under-explored. GCEs generate a new graph similar to the original one, with a different outcome grounded on the underlying predictive model. Among these GCE techniques, those rooted in generative mechanisms have received relatively limited investigation despite demonstrating impressive accomplishments in other domains, such as artistic styles and natural language modelling. The preference for generative explainers stems from their capacity to generate counterfactual instances during inference, leveraging autonomously acquired perturbations of the input graph. Motivated by the rationales above, our study introduces RSGG-CE, a novel Robust Stochastic Graph Generator for Counterfactual Explanations able to produce counterfactual examples from the learned latent space considering a partially ordered generation sequence. Furthermore, we undertake quantitative and qualitative analyses to compare RSGG-CE's performance against SoA generative explainers, highlighting its increased ability to engendering plausible counterfactual candidates.

show abstract

“…On the other end of the spectrum of explainability, we find inherently interpretable white-box prediction models (Loyola-González 2019), which are preferred for decisionmaking purposes (Verenich et al 2019). Alas, black-box models demonstrate superior performance and generalisation capabilities when dealing with high-dimensional data (Aragona et al 2021;Ding et al 2019;Feng, Tang, and Liu 2019;Huang et al 2020;Madeddu, Stilo, and Velardi 2020;Prenkaj et al 2021Prenkaj et al , 2020Prenkaj et al , 2023aVerma, Mandal, and Gupta 2022;Wang, Yu, and Miao 2017).…”

Section: Introductionmentioning

confidence: 99%

Robust Stochastic Graph Generator for Counterfactual Explanations

Prado-Romero,

Prenkaj,

Stilo

2024

AAAI

1

0

View full text Add to dashboard Cite

Counterfactual Explanation (CE) techniques have garnered attention as a means to provide insights to the users engaging with AI systems. While extensively researched in domains such as medical imaging and autonomous vehicles, Graph Counterfactual Explanation (GCE) methods have been comparatively under-explored. GCEs generate a new graph similar to the original one, with a different outcome grounded on the underlying predictive model. Among these GCE techniques, those rooted in generative mechanisms have received relatively limited investigation despite demonstrating impressive accomplishments in other domains, such as artistic styles and natural language modelling. The preference for generative explainers stems from their capacity to generate counterfactual instances during inference, leveraging autonomously acquired perturbations of the input graph. Motivated by the rationales above, our study introduces RSGG-CE, a novel Robust Stochastic Graph Generator for Counterfactual Explanations able to produce counterfactual examples from the learned latent space considering a partially ordered generation sequence. Furthermore, we undertake quantitative and qualitative analyses to compare RSGG-CE's performance against SoA generative explainers, highlighting its increased ability to engendering plausible counterfactual candidates.

show abstract