Abstract
Graphs have been widely used to represent complex data in many applications, such as e-commerce, social networks, and bioinformatics. Efficient and effective analysis of graph data is important for graph-based applications. However, most graph analysis tasks are combinatorial optimization (CO) problems, which are NP-hard. Recent studies have focused a lot on the potential of using machine learning (ML) to solve graph-based CO problems. Most recent methods follow the two-stage framework. The first stage is graph representation learning, which embeds the graphs into low-dimension vectors. The second stage uses machine learning to solve the CO problems using the embeddings of the graphs learned in the first stage. The works for the first stage can be classified into two categories, graph embedding methods and end-to-end learning methods. For graph embedding methods, the learning of the the embeddings of the graphs has its own objective, which may not rely on the CO problems to be solved. The CO problems are solved by independent downstream tasks. For end-to-end learning methods, the learning of the embeddings of the graphs does not have its own objective and is an intermediate step of the learning procedure of solving the CO problems. The works for the second stage can also be classified into two categories, non-autoregressive methods and autoregressive methods. Non-autoregressive methods predict a solution for a CO problem in one shot. A non-autoregressive method predicts a matrix that denotes the probability of each node/edge being a part of a solution of the CO problem. The solution can be computed from the matrix using search heuristics such as beam search. Autoregressive methods iteratively extend a partial solution step by step. At each step, an autoregressive method predicts a node/edge conditioned to current partial solution, which is used to its extension. In this survey, we provide a thorough overview of recent studies of the graph learning-based CO methods. The survey ends with several remarks on future research directions.
Highlights
Graphs are ubiquitous and are used in a wide range of domains, from e-commerce [21, 78] to social networking [31, 70] to bioinformatics [20, 76]
The encoder of pointer network (Ptr-Net) is an recurrent neural network (RNN) taking the nodes of the graph G as input and outputting an embedding of G, where the order of the nodes is randomly chosen
We provided a thorough overview of the recent graph learning methods for solving combinatorial optimization (CO) problems
Summary
Graphs are ubiquitous and are used in a wide range of domains, from e-commerce [21, 78] to social networking [31, 70] to bioinformatics [20, 76]. Many graph analysis tasks are combinatorial optimization (CO) problems, such as the traveling salesman problem (TSP) [67], maximum independent set (MIS) [14], maximum cut (MaxCut) [23], minimum vertex cover (MVC) [42], maximum clique (MC) [10], graph coloring (GC) [54], subgraph isomorphism (SI) [22], and graph similarity (GSim) [55]. Despite having no theoretical guarantee of optimality, heuristic algorithms often produce good enough solutions in practice
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
