New Knapsack Problem solution with neural network approach

Question

While I was learning the Constraint Satisfaction Problems, I analyzed the Knapsack problem(https://www.csplib.org/Problems/prob133/) and I saw the approach with the neural network was not the best approach in solving this problem since it has not shown the best results. Knowing that the neural network approach has shown great results in other CSPs, I was wondering if we can improve the already used algorithm to improve the results, is anybody here who has already seen something similar in progress or that would like to work together and find any possible approach?