Selective Network Discovery via Deep Reinforcement Learning on Embedded Spaces

TL;DR

This paper introduces NAC, a deep reinforcement learning framework for task-specific network discovery in incomplete networks, improving efficiency and effectiveness in collecting vertices with desired attributes.

Contribution

The paper proposes a novel offline RL approach, Network Actor Critic (NAC), utilizing task-specific embeddings for efficient, goal-oriented network exploration in resource-constrained settings.

Findings

NAC outperforms online algorithms in synthetic and real benchmarks.

Task-specific embeddings enhance offline planning effectiveness.

Offline reward models significantly improve network discovery performance.

Abstract

Complex networks are often either too large for full exploration, partially accessible, or partially observed. Downstream learning tasks on these incomplete networks can produce low quality results. In addition, reducing the incompleteness of the network can be costly and nontrivial. As a result, network discovery algorithms optimized for specific downstream learning tasks given resource collection constraints are of great interest. In this paper, we formulate the task-specific network discovery problem in an incomplete network setting as a sequential decision making problem. Our downstream task is selective harvesting, the optimal collection of vertices with a particular attribute. We propose a framework, called Network Actor Critic (NAC), which learns a policy and notion of future reward in an offline setting via a deep reinforcement learning algorithm. The NAC paradigm utilizes a task-specific network embedding to reduce the state space complexity. A detailed comparative analysis of popular network embeddings is presented with respect to their role in supporting offline planning. Furthermore, a quantitative study is presented on several synthetic and real benchmarks using NAC and several baselines. We show that offline models of reward and network discovery policies lead to significantly improved performance when compared to competitive online discovery algorithms. Finally, we outline learning regimes where planning is critical in addressing sparse and changing reward signals.