Poster
Meta-Learning Neural Bloom Filters
Jack Rae · Sergey Bartunov · Timothy Lillicrap

Thu Jun 13th 06:30 -- 09:00 PM @ Pacific Ballroom #43
in Posters Thu »

There has been a recent trend in training neural networks to replace data structures that have been crafted by hand, with an aim for faster execution, better accuracy, or greater compression. In this setting, a neural data structure is instantiated by training a network over many epochs of its inputs until convergence. In applications where inputs arrive at high throughput, or are ephemeral, training a network from scratch is not practical. This motivates the need for few-shot neural data structures. In this paper we explore the learning of approximate set membership over a set of data in one-shot via meta-learning. We propose a novel memory architecture, the Neural Bloom Filter, which is able to achieve significant compression gains over classical Bloom Filters and existing memory-augmented neural networks.

Keywords: Algorithms · Deep Sequence Models · Systems and Software

Author Information

Jack Rae (DeepMind)
Sergey Bartunov (DeepMind)
Tim Lillicrap (Google DeepMind)

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

More from the Same Authors