Timezone: »

MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
Sami Abu-El-Haija · Bryan Perozzi · Amol Kapoor · Nazanin Alipourfard · Kristina Lerman · Hrayr Harutyunyan · Greg Ver Steeg · Aram Galstyan

Wed Jun 12 06:30 PM -- 09:00 PM (PDT) @ Pacific Ballroom #88

Existing popular methods for semi-supervised learning with Graph Neural Networks (such as the Graph Convolutional Network) provably cannot learn a general class of neighborhood mixing relationships. To address this weakness, we propose a new model, MixHop, that can learn these relationships, including difference operators, by repeatedly mixing feature representations of neighbors at various distances. MixHop requires no additional memory or computational complexity, and outperforms on challenging baselines. In addition, we propose sparsity regularization that allows us to visualize how the network prioritizes neighborhood information across different graph datasets. Our analysis of the learned architectures reveals that neighborhood mixing varies per datasets.

Author Information

Sami Abu-El-Haija (USC Information Sciences Institute)
Bryan Perozzi (Google AI)
Amol Kapoor (Google Research)
Nazanin Alipourfard (University of Southern California)
Kristina Lerman (ISI, University of Southern California)
Hrayr Harutyunyan (University of Southern California)
Greg Ver Steeg (University of Southern California)
Aram Galstyan (USC ISI)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors