Graph Convolutional Networks (GCNs) elaborate the expressive power of deep learning from grid-like data to graph-structured data and have achieved remarkable success in a wide variety of domains [7, 6, 13, 27, 22, 30, 1, 8, 42, 18, 31, 12, 41, 19]. Just like CNNs, modern GCNs could promisingly learn both the local and global structural patterns of graphs through designed convolutions. However, the vulnerability of GCNs against adversarial attacks has been revealed recently [70, 11, 9]. The lack of robustness arouses concerns on applying GCNs in a variety of fields pertaining to security and privacy.

We also show that MatrixNet respects group relations allowing generalization to group elements of greater word length than in the training set.

Clustering is an important technique for identifying structural information in large-scale data analysis, where the underlying dataset may be too large to store.

In the hospital, patients may be in the ICU with ECG/PPG sensors to monitor their already-poor healthcondition. ML methods must rely onlearning toimpute missing signals based onthesignal that is present, rather than learning tocreate ageneral-purpose imputation template thatmimics standard healthybehavior. Likewise, participant movement inboth contexts can result in artifacts(e.g. Inabroadercontext, we want to match the high quality level of other datasets such as PTB-XL, in which 77.01% of thesignal data areofhighest assessed quality [18]. See below for examples of ECG signals with their associated periodogram.

The promise of mobile health (mHealth) is the ability to use wearable sensors to monitor participant physiology athigh frequencies during daily life to enable temporally-precise health interventions.

Weaddress these limitations byproposing a Probabilistic Transformer1 (ProbTransformer) that models a hierarchical latent distribution and performs sampling in the latent space.