Dataless Neural Networks for Resource-Constrained Project Scheduling
This addresses the RCPSP, a combinatorial optimization problem, by enabling GPU parallelization for scheduling, but it is incremental as it extends existing dataless methods to a new domain.
The paper introduces the first dataless neural network approach for the Resource-Constrained Project Scheduling Problem (RCPSP), eliminating the need for training data by encoding problem instances into network parameters and using gradient-based optimization, with empirical results pending on benchmark instances.
Dataless neural networks represent a paradigm shift in applying neural architectures to combinatorial optimization problems, eliminating the need for training datasets by encoding problem instances directly into network parameters. Despite the pioneering work of Alkhouri et al. (2022) demonstrating the viability of dataless approaches for the Maximum Independent Set problem, our comprehensive literature review reveals that no published work has extended these methods to the Resource-Constrained Project Scheduling Problem (RCPSP). This paper addresses this gap by presenting the first dataless neural network approach for RCPSP, providing a complete mathematical framework that transforms discrete scheduling constraints into differentiable objectives suitable for gradient-based optimization. Our approach leverages smooth relaxations and automatic differentiation to unlock GPU parallelization for project scheduling, traditionally a domain of sequential algorithms. We detail the mathematical formulation for both precedence and renewable resource constraints, including a memory-efficient dense time-grid representation. Implementation and comprehensive experiments on PSPLIB benchmark instances (J30, J60, and J120) are currently underway, with empirical results to be reported in an updated version of this paper.