I think you’re on the right track that trees are good at feature engineering. But the key problem is that DL researchers are horrible at feature engineering, because they have never had to do it. These folks included.
The feature engineering they do here is absolutely horrible! They use a QuantileTransform and that’s it. They don’t even tune the critical hyper parameter of the number of quantiles. Do they always use the scikitlearn default of 1,000 quantiles? No wonder uninformative features are hurting- they are getting expanded into 1000 even more uninformative features! Also with a single quantile transform like that, the relative values of the quantiles are completely lost! If the values 86 and 87 fall into different bins, the model has literally no information that the two bins are similar to each other, or even that they come from the same raw input.
For a very large dataset a NN would learn its way around this kind of bone headed mistake. But for this size dataset, these researchers have absolutely crippled the nets with this thoughtless approach to feature engineering.
There is plenty more to criticize about their experiments, but it’s probably less important. E.g. Their HP ranges are too small to allow for the kind of nets that are known to work best in the modern era (after Double Descent theory has been worked out) - large heavily regularized nets. They don’t let the nets get very big and they don’t let the regularization get nearly big enough.
So. Bad comparison. But it’s also very true that XGB “just works” most of the time. NN’s are finicky and complicated and very few people really understand them well enough to apply them to novel situations. Those who do are working on fancy AI problems, not writing poor comparison papers like this one.