Lense: Learning to navigate subgraph embeddings for large-scale combinatorial optimisation

D Ireland, G Montana - International conference on machine …, 2022 - proceedings.mlr.press
Combinatorial Optimisation problems arise in several application domains and are often
formulated in terms of graphs. Many of these problems are NP-hard, but exact solutions are …

Learning heuristics over large graphs via deep reinforcement learning

S Manchanda, A Mittal, A Dhawan, S Medya… - arXiv preprint arXiv …, 2019 - arxiv.org
There has been an increased interest in discovering heuristics for combinatorial problems
on graphs through machine learning. While existing techniques have primarily focused on …

Influence maximization in unknown social networks: Learning policies for effective graph sampling

H Kamarthi, P Vijayan, B Wilder, B Ravindran… - arXiv preprint arXiv …, 2019 - arxiv.org
A serious challenge when finding influential actors in real-world social networks is the lack
of knowledge about the structure of the underlying network. Current state-of-the-art methods …

Learning combinatorial optimization algorithms over graphs

E Khalil, H Dai, Y Zhang, B Dilkina… - Advances in neural …, 2017 - proceedings.neurips.cc
The design of good heuristics or approximation algorithms for NP-hard combinatorial
optimization problems often requires significant specialized knowledge and trial-and-error …

Deep graph representation learning and optimization for influence maximization

C Ling, J Jiang, J Wang, MT Thai… - International …, 2023 - proceedings.mlr.press
Influence maximization (IM) is formulated as selecting a set of initial users from a social
network to maximize the expected number of influenced users. Researchers have made …

Deep graph representation learning for influence maximization with accelerated inference

T Chowdhury, C Ling, J Jiang, J Wang, MT Thai… - Neural Networks, 2024 - Elsevier
Selecting a set of initial users from a social network in order to maximize the envisaged
number of influenced users is known as influence maximization (IM). Researchers have …

Adversarial graph embeddings for fair influence maximization over social networks

M Khajehnejad, AA Rezaei, M Babaei… - arXiv preprint arXiv …, 2020 - arxiv.org
Influence maximization is a widely studied topic in network science, where the aim is to
reach the maximum possible number of nodes, while only targeting a small initial set of …

Gcomb: Learning budget-constrained combinatorial algorithms over billion-sized graphs

S Manchanda, A Mittal, A Dhawan… - Advances in …, 2020 - proceedings.neurips.cc
There has been an increased interest in discovering heuristics for combinatorial problems
on graphs through machine learning. While existing techniques have primarily focused on …

Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective

VA Darvariu, S Hailes, M Musolesi - arXiv preprint arXiv:2404.06492, 2024 - arxiv.org
Graphs are a natural representation for systems based on relations between connected
entities. Combinatorial optimization problems, which arise when considering an objective …

Grain: Improving data efficiency of graph neural networks via diversified influence maximization

W Zhang, Z Yang, Y Wang, Y Shen, Y Li… - arXiv preprint arXiv …, 2021 - arxiv.org
Data selection methods, such as active learning and core-set selection, are useful tools for
improving the data efficiency of deep learning models on large-scale datasets. However …