DeepAI AI Chat
Log In Sign Up

Meta-Learning Neural Bloom Filters

by   Jack W Rae, et al.

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.


In oder Aus

Bloom filters are data structures used to determine set membership of el...

EMO: Episodic Memory Optimization for Few-Shot Meta-Learning

Few-shot meta-learning presents a challenge for gradient descent optimiz...

Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks

Few-shot learning for neural networks (NNs) is an important problem that...

Compressing (Multidimensional) Learned Bloom Filters

Bloom filters are widely used data structures that compactly represent s...

Labeled Memory Networks for Online Model Adaptation

Augmenting a neural network with memory that can grow without growing th...

Optimizing Cuckoo Filter for high burst tolerance,low latency, and high throughput

In this paper, we present an implementation of a cuckoo filter for membe...

NeuralVDB: High-resolution Sparse Volume Representation using Hierarchical Neural Networks

We introduce NeuralVDB, which improves on an existing industry standard ...