Timezone: »

Semi-Implicit Graph Variational Auto-Encoders
Arman Hasanzadeh · Ehsan Hajiramezanali · Krishna Narayanan · Nick Duffield · Mingyuan Zhou · Xiaoning Qian

Wed Dec 05:00 PM -- 07:00 PM PST @ East Exhibition Hall B + C #190

Semi-implicit graph variational auto-encoder (SIG-VAE) is proposed to expand the flexibility of variational graph auto-encoders (VGAE) to model graph data. SIG-VAE employs a hierarchical variational framework to enable neighboring node sharing for better generative modeling of graph dependency structure, together with a Bernoulli-Poisson link decoder. Not only does this hierarchical construction provide a more flexible generative graph model to better capture real-world graph properties, but also does SIG-VAE naturally lead to semi-implicit hierarchical variational inference that allows faithful modeling of implicit posteriors of given graph data, which may exhibit heavy tails, multiple modes, skewness, and rich dependency structures. SIG-VAE integrates a carefully designed generative model, well suited to model real-world sparse graphs, and a sophisticated variational inference network, which propagates the graph structural information and distribution uncertainty to capture complex posteriors. SIG-VAE clearly outperforms a simple combination of VGAE with variational inference, including semi-implicit variational inference~(SIVI) or normalizing flow (NF), which does not propagate uncertainty in its inference network, and provides more interpretable latent representations than VGAE does. Extensive experiments with a variety of graph data show that SIG-VAE significantly outperforms state-of-the-art methods on several different graph analytic tasks.

Author Information

Arman Hasanzadeh (Texas A&M University)
Ehsan Hajiramezanali (Texas A&M University)
Krishna Narayanan (Texas A&M University)
Nick Duffield (Texas A&M University)
Mingyuan Zhou (University of Texas at Austin)
Xiaoning Qian (Texas A&M)

More from the Same Authors