Well the whole "deep learning" revolution really only started around 2012 when the ImageNet competition was won with a neural net. There have been numerous small breakthroughs that collectively have made deep neural nets now easy to train, and neural nets now provide state-of-the art (and often human-level) results in areas such as image recognition, speech recognition and language translation.
There's also been a revival of reinforcement learning, especially when used together with neural nets ("deep reinforcement learning"), and again there have been many small advances that collectively make this work very well. This is the technology that powered Google's AlphaGo to beat the world champion at the board game of "Go", not to mention learning how to play many arcade games at beyond human level based only on the raw pixels and current score as input.
There have also been tremendous strides in AI hype leading folk to fear the robot uprising based on these more mundane machine-learning/neural-net breakthroughs!
Scaled-ELU is meant to create self-normalizing nets, but that's nothing you can't achieve a bit less efficiently with explicit normalization (batch norm, etc), so hardly a game changer.
I don't now about radically different.. after all a graph is just a bunch of nodes, edges and associated attributes. There are standard alternatives to the DOT/GV graph description language though, such as GraphML (XML based) and GML (others too, but these seem to be most supported).
For graph layout, tools worth looking at include OGDF (an open source C++ library), the commercial yFiles Java library with free yEd editor/layout tool (includes support for GraphML attributes), and Gephi (an open source Java-based graph layout/visualization tool).
If your graph represents some type of directed dataflow, then maybe Google's Tensorboard graph visualizer (intended primarily for neural nets) is of interest - it's open source and very slick (esp. wrt subgraph collapsing/expanding), but you'd be on your own in terms of importing a foreign graph format.
There's also been a revival of reinforcement learning, especially when used together with neural nets ("deep reinforcement learning"), and again there have been many small advances that collectively make this work very well. This is the technology that powered Google's AlphaGo to beat the world champion at the board game of "Go", not to mention learning how to play many arcade games at beyond human level based only on the raw pixels and current score as input.
There have also been tremendous strides in AI hype leading folk to fear the robot uprising based on these more mundane machine-learning/neural-net breakthroughs!