Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

GraMeR: Graph Meta Reinforcement learning for multi-objective influence maximization

Journal Article · · Journal of Parallel and Distributed Computing
 [1];  [2];  [1]
  1. Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
  2. Kansas State Univ., Manhattan, KS (United States)
+ Show Author Affiliations
Influence maximization (IM) is a combinatorial problem of identifying a subset of seed nodes in a network (graph), which when activated, provide a maximal spread of influence in the network for a given diffusion model and a budget for seed set size. IM has numerous applications such as viral marketing, epidemic control, sensor placement and other network-related tasks. However, its practical uses are limited due to the computational complexity of current algorithms. Recently, deep reinforcement learning has been leveraged to solve IM in order to ease the computational burden. However, there are serious limitations in current approaches, including narrow IM formulation that only consider influence via spread and ignore self-activation, low scalability to large graphs, and lack of generalizability across graph families leading to a large running time for every test network. In this work, we address these limitations through a unique approach that involves: (1) Formulating a generic IM problem as a Markov decision process that handles both intrinsic and influence activations; (2)incorporating generalizability via meta-learning across graph families. There are previous works that combine deep reinforcement learning with graph neural network, but this work solves a more realistic IM problem and incorporates generalizability across graphs via meta reinforcement learning. Extensive experiments are carried out in various standard networks to validate performance of the proposed Graph Meta Reinforcement learning (GraMeR) framework. Finally, the results indicate that GraMeR is multiple orders faster and generic than conventional approaches when applied on small to medium scale graphs.
Research Organization:
Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
Sponsoring Organization:
National Science Foundation (NSF); USDOE
Grant/Contract Number:
AC05-76RL01830
OSTI ID:
2378038
Report Number(s):
PNNL-SA--198119
Journal Information:
Journal of Parallel and Distributed Computing, Journal Name: Journal of Parallel and Distributed Computing Vol. 192; ISSN 0743-7315
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (15)

Q-learning journal May 1992
Network-based intervention strategies to reduce violence among homeless journal July 2019
Network structure and minimum degree journal September 1983
A multi-objective deep reinforcement learning framework journal November 2020
A reinforcement learning approach for optimizing multiple traveling salesman problems over graphs journal September 2020
GRL: Knowledge graph completion with GAN-based reinforcement learning journal December 2020
Scalable graph neural network-based framework for identifying critical nodes and links in complex networks journal January 2022
Robustness assessment of Hetero-functional graph theory based model of interdependent urban utility networks journal August 2021
Reinforcement Learning, Fast and Slow journal May 2019
Hybrid computing using a neural network with dynamic external memory journal October 2016
Finding key players in complex networks through deep reinforcement learning journal May 2020
Growing scale-free networks with tunable clustering journal January 2002
Learning Hidden Influences in Large-Scale Dynamical Social Networks: A Data-Driven Sparsity-Based Approach, in Memory of Roberto Tempo journal October 2021
Influence Maximization on Social Graphs: A Survey journal October 2018
The Optimizer’s Curse: Skepticism and Postdecision Surprise in Decision Analysis journal March 2006

Similar Records

Related Subjects

97 MATHEMATICS AND COMPUTING
Artificial Intelligence (AI)/Machine Learning (ML)
Q learning
combinatorial algorithms
graph algorithms
graph neural networks
influence maximization
meta learning
multi-objective
reinforcement learning