Skip to yearly menu bar Skip to main content

Workshop: Geometrical and Topological Representation Learning

Message Passing Neural Processes

Catalina Cangea · Ben Day · Arian Jamasb · Pietro Lio

Keywords: [ few-shot learning ] [ message passing ] [ neural processes ] [ node classification ] [ active learning ] [ uncertainty ] [ graph representation learning ]


Neural Processes (NPs) are powerful and flexible models able to incorporate uncertainty when representing stochastic processes, while maintaining a linear time complexity. However, NPs produce a latent description by aggregating independent representations of context points and lack the ability to exploit relational information present in many datasets. This renders NPs ineffective in settings where the stochastic process is primarily governed by neighbourhood rules, such as cellular automata (CA), and limits performance for any task where relational information remains unused. We address this shortcoming by introducing Message Passing Neural Processes (MPNPs), the first class of NPs that explicitly makes use of relational structure within the model. Our evaluation shows that MPNPs thrive at lower sampling rates, on existing benchmarks and newly-proposed CA and Cora-Branched tasks. We further report strong generalisation over density-based CA rule-sets and significant gains in challenging arbitrary-labelling and few-shot learning setups.

Chat is not available.