Learning Heuristics over Large Graphs via Deep Reinforcement Learning
This addresses scalability and budget constraints for combinatorial graph problems, offering significant speed improvements for practical applications like Influence Maximization, though it is incremental in method.
The paper tackles the problem of scaling heuristic learning for combinatorial graph problems to billion-sized graphs under budget constraints, proposing GCOMB, which is 100 times faster than state-of-the-art methods with similar or better quality, and 150 times faster for Influence Maximization.
There has been an increased interest in discovering heuristics for combinatorial problems on graphs through machine learning. While existing techniques have primarily focused on obtaining high-quality solutions, scalability to billion-sized graphs has not been adequately addressed. In addition, the impact of budget-constraint, which is necessary for many practical scenarios, remains to be studied. In this paper, we propose a framework called GCOMB to bridge these gaps. GCOMB trains a Graph Convolutional Network (GCN) using a novel probabilistic greedy mechanism to predict the quality of a node. To further facilitate the combinatorial nature of the problem, GCOMB utilizes a Q-learning framework, which is made efficient through importance sampling. We perform extensive experiments on real graphs to benchmark the efficiency and efficacy of GCOMB. Our results establish that GCOMB is 100 times faster and marginally better in quality than state-of-the-art algorithms for learning combinatorial algorithms. Additionally, a case-study on the practical combinatorial problem of Influence Maximization (IM) shows GCOMB is 150 times faster than the specialized IM algorithm IMM with similar quality.