Graph-based Heuristic Search for Module Selection Procedure in Neural Module Network
Neural Module Network (NMN) is a machine learning model for solving the visual question answering tasks. NMN uses programs to encode modules' structures, and its modularized architecture enables it to solve logical problems more reasonably. However, because of the non-differentiable procedure of module selection, NMN is hard to be trained end-to-end. To overcome this problem, existing work either included ground-truth program into training data or applied reinforcement learning to explore the program. However, both of these methods still have weaknesses. In consideration of this, we proposed a new learning framework for NMN. Graph-based Heuristic Search is the algorithm we proposed to discover the optimal program through a heuristic search on the data structure named Program Graph. Our experiments on FigureQA and CLEVR dataset show that our methods can realize the training of NMN without ground-truth programs and achieve superior efficiency over existing reinforcement learning methods in program exploration.
Code (0)
등록된 구현이 없습니다.
Tasks
Heuristic SearchQuestion Answeringreinforcement-learningReinforcement LearningReinforcement Learning (RL)Visual Question AnsweringVisual Question Answering (VQA)Similar Papers 제목 키워드 기반
Learning a Generic Value-Selection Heuristic Inside a Constraint Programming Solver
Constraint programming is known for being an efficient approach for solving combinatorial problems. Important design choices in a solver are the branching heuristics, which are designed to lead the search to the best sol…
Graph Neural NetworkQ-LearningVariable SelectionEnumerating Distinct Decision Trees
The search space for the feature selection problem in decision tree learning is the lattice of subsets of the available features. We provide an exact enumeration procedure of the subsets that lead to all and only th…
feature selectionLarge Neighborhood Search based on Neural Construction Heuristics
We propose a Large Neighborhood Search (LNS) approach utilizing a learned construction heuristic based on neural networks as repair operator to solve the vehicle routing problem with time windows (VRPTW). Our method uses…
reinforcement-learningReinforcement Learning (RL)Optimal Kernel Choice for Score Function-based Causal Discovery
Score-based methods have demonstrated their effectiveness in discovering causal relationships by scoring different causal structures based on their goodness of fit to the data. Recently, Huang et al. proposed a generaliz…
Causal DiscoveryA new selection strategy for selective cluster ensemble based on Diversity and Independency
This research introduces a new strategy in cluster ensemble selection by using Independency and Diversity metrics. In recent years, Diversity and Quality, which are two metrics in evaluation procedure, have been used for…
ClusteringDiversitysoftware testing