Skip to main content

Research Repository

Advanced Search

A Neural Approach to Generation of Constructive Heuristics

Alissa, Mohamad; Sim, Kevin; Hart, Emma


Mohamad Alissa


Both algorithm-selection methods and hyper-heuristic methods rely on a pool of complementary heuristics. Improving the pool with new heuristics can improve performance, however, designing new heuristics can be challenging. Methods such as genetic programming have proved successful in automating this process in the past. Typically, these make use of problem state-information and existing heuristics as components. Here we propose a novel neural approach for generating constructive heuristics, in which a neural network acts as a heuristic by generating decisions. We evaluate two architectures, an Encoder-Decoder LSTM and a Feed-Forward Neural Network. Both are trained using the decisions output from existing heuristics on a large set of instances. We consider streaming instances of bin-packing problems in a continual stream that must be packed immediately in strict order and using a limited number of resources. We show that the new heuristics generated are capable of solving a subset of instances better than the well-known heuristics forming the original pool, and hence the overall value of the pool is improved w.r.t. both Falkenauer's performance metric and the number of bins used.


Alissa, M., Sim, K., & Hart, E. (2021). A Neural Approach to Generation of Constructive Heuristics. In 2021 IEEE Congress on Evolutionary Computation (CEC) (1147-1154).

Conference Name IEEE Congress on Evolutionary Computation 2021
Conference Location Kraków, Poland (online)
Start Date Jun 28, 2021
End Date Jul 1, 2021
Acceptance Date Apr 7, 2021
Online Publication Date Aug 9, 2021
Publication Date 2021
Deposit Date Jul 5, 2021
Publicly Available Date Jul 5, 2021
Publisher Institute of Electrical and Electronics Engineers
Pages 1147-1154
Book Title 2021 IEEE Congress on Evolutionary Computation (CEC)
Keywords Automatic Heuristics Generation; Hyper-Heuristics; Encoder-Decoder LSTM; Streaming Bin-packing
Public URL


A Neural Approach To Generation Of Constructive Heuristics (3.6 Mb)

Copyright Statement

You might also like

Downloadable Citations