The ARMA GNN layer implements a rational graph filter with a recursive approximation.

GeniePath is a scalable approach for learning adaptive receptive fields of neural networks defined on permutation invariant graph data. In GeniePath, we propose an adaptive path layer consists of two complementary functions designed for breadth and depth exploration respectively, where the former learns the importance of different sized neighborhoods, while the latter extracts and filters signals aggregated from neighbors of different hops away.

Description and image from: [GeniePath: Graph Neural Networks with Adaptive Receptive Paths](https://arxiv.org/pdf/1802.00910.pdf)

GeniePath

GeniePath: Graph Neural Networks with Adaptive Receptive Paths

ARMA

Graph Neural Networks with convolutional ARMA filters

**RoBERTa** is an extension of [BERT](https://paperswithcode.com/method/bert) with changes to the pretraining procedure. The modifications include: 

- training the model longer, with bigger batches, over more data
- removing the next sentence prediction objective
- training on longer sequences
- dynamically changing the masking pattern applied to the training data. The authors also collect a large new dataset ($\text{CC-News}$) of comparable size to other privately used datasets, to better control for training set size effects

Source	Graph Neural Networks with convolutional ARMA filters
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com