Skip to yearly menu bar Skip to main content

In-Person Poster presentation / poster accept

Semi-Parametric Inducing Point Networks and Neural Processes

Richa Rastogi · Yair Schiff · Alon Hacohen · Zhaozhi Li · Yi-Yuan Lee · Yuntian Deng · Mert Sabuncu · Volodymyr Kuleshov

MH1-2-3-4 #44

Keywords: [ Deep Learning and representational learning ]


We introduce semi-parametric inducing point networks (SPIN), a general-purpose architecture that can query the training set at inference time in a compute-efficient manner. Semi-parametric architectures are typically more compact than parametric models, but their computational complexity is often quadratic. In contrast, SPIN attains linear complexity via a cross-attention mechanism between datapoints inspired by inducing point methods. Querying large training sets can be particularly useful in meta-learning, as it unlocks additional training signal, but often exceeds the scaling limits of existing models. We use SPIN as the basis of the Inducing Point Neural Process, a probabilistic model which supports large contexts in meta-learning and achieves high accuracy where existing models fail. In our experiments, SPIN reduces memory requirements, improves accuracy across a range of meta-learning tasks, and improves state-of-the-art performance on an important practical problem, genotype imputation.

Chat is not available.