Neural Priority Queues for Graph Neural Networks
Graph Neural Networks (GNNs) have shown considerable success in neural algorithmic reasoning. Many traditional algorithms make use of an explicit memory in the form of a data structure. However, there has been limited exploration on augmenting GNNs with external memory. In this paper, we present Neural Priority Queues, a differentiable analogue to algorithmic priority queues, for GNNs. We propose and motivate a desiderata for memory modules, and show that Neural PQs exhibit the desiderata, and reason about their use with algorithmic reasoning. This is further demonstrated by empirical results on the CLRS-30 dataset. Furthermore, we find the Neural PQs useful in capturing long-range interactions, as empirically shown on a dataset from the Long-Range Graph Benchmark.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph RegressionSimilar Papers 제목 키워드 기반
Learning-Augmented Priority Queues
Priority queues are one of the most fundamental and widely used data structures in computer science. Their primary objective is to efficiently support the insertion of new elements with assigned priorities and the extrac…
Learning Treatment Effects during Resource Allocation via Priority-Queue Randomization
Public service programs often allocate limited resources under uncertainty about their benefits, creating a need for randomization to support credible evaluation. In practice, however, applicants commonly enter waitlists…
Algorithms for Grey-Weighted Distance Computations
With the increasing size of datasets and demand for real time response for interactive applications, improving runtime for algorithms with excessive computational requirements has become increasingly important. Many diff…
Enhanced Methods for the Weight Constrained Shortest Path Problem
The classic problem of constrained pathfinding is a well-studied, yet challenging, topic in AI with a broad range of applications in various areas such as communication and transportation. The Weight Constrained Shortest…
Learning in Strategic Queuing Systems with Small Buffers
Routers in networking use simple learning algorithms to find the best way to deliver packets to their desired destination. This simple, myopic and distributed decision system makes large queuing systems simple to operate…