Robust Representation for Graph Data
Modern data are usually high-dimensional with noise and corruption. A useful representation of data has to be robust and address the data structure. In this talk, I will first present a class of robust models called the scattering transform that can be used to generated features from graph data. In graph scattering transforms, the representation is generated in an unsupervised manner based on graph wavelets. It is approximately invariant to permutations and stable to signal or graph manipulations. Numerical results show that it works effectively for classification and community detection problems. Next, I will address how the structure of data can be found using autoencoders. Indeed, in the framework of autoencoders, graph scattering transform can be applied to the important task of graph generation. It shows state-of-the-art performance in link prediction and can be used to generate molecular samples.