… Our work aims to establish a fair comparison of them and identify the … main deep architectures
that we highlight in our work, as well as the existing solutions included in the comparison. …

… Furthermore, we provide the comparison results of FairINV and baseline methods in multi-sensitive
attribute scenarios, as detailed in the Appendix B. We make the following …

… . (In order to make fair comparisons, the training of the MP based machine learning algorithms
was adjusted for survival data; see the Supplementary Material for details.) Comparisons …

… An end-to-end deep learning architecture for graph classification. In: McIlraith, SA, Weinberger,
KQ (eds.) Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (…

… In this section, we provide comparison of the proposed model to the state-of-the-arts. … For
a fair comparison and without lose of generality, all models are trained on Liberty (DeepDesc [5…

… problem of learning fair policies in (deep) cooperative multi-agent reinforcement learning (…
In experiments, we demonstrate the importance of the two sub-networks for fair optimization. …

… In order to have a fair comparison, not only different modeling options should be considered,
but also the hyperparameters of the models should be optimized. In particular, considering …

… strategy on four datasets; E: Comparison of different active learning strategies on the Diabetic
… We now present results for SSD, the deep learning based anomaly detection approach, as …

… wide range of datasets for fair evaluation and comparison, including both conventional non-…
and enables fair evaluation. Unlike the current tools that are limited to certain deep learning …

… [24], in order to enable fair comparisons. They use half of the available data for validation. …
For a fair comparison with [21], we kept the fc6 and fc7 layers of VGG and eliminated the …