arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.11072cs.AIcs.LGstat.ML
收藏

SATNet的符号接地技术

Techniques for Symbol Grounding with SATNet

McGill University(麦吉尔大学);NVIDIA(英伟达);Mila – Quebec AI Institute(米拉-魁北克人工智能研究所)

Sever Topan, David Rolnick, Xujie Si

摘要:

许多专家认为,人工智能的未来受到该领域将符号逻辑推理集成到深度学习架构中的能力的限制。最近提出的可微MAXSAT求解器SATNet在与传统神经网络集成并解决视觉推理问题的能力上是一个突破。例如,它可以纯粹从图像示例中学习数独规则。尽管SATNet取得了成功,但它被证明屈服于神经符号系统中的一个关键挑战,即符号基础问题:在没有明确监督的情况下,无法将视觉输入映射到符号变量(“标签泄漏”)。在这项工作中,我们提出了一个自我监督的预训练管道,使SATNet能够克服这一限制,从而扩大了SATNet架构可以解决的问题的类别,包括根本没有中间标签的数据集。我们证明,我们的方法允许SATNet达到完全的准确性,即使有一个更难的问题设置,防止任何标签泄漏。我们还引入了一种校对方法,进一步提高了SATNet架构的性能,击败了Visual Sudoku上的最先进技术。

英文摘要:

Many experts argue that the future of artificial intelligence is limited by the field's ability to integrate symbolic logical reasoning into deep learning architectures. The recently proposed differentiable MAXSAT solver, SATNet, was a breakthrough in its capacity to integrate with a traditional neural network and solve visual reasoning problems. For instance, it can learn the rules of Sudoku purely from image examples. Despite its success, SATNet was shown to succumb to a key challenge in neurosymbolic systems known as the Symbol Grounding Problem: the inability to map visual inputs to symbolic variables without explicit supervision ("label leakage"). In this work, we present a self-supervised pre-training pipeline that enables SATNet to overcome this limitation, thus broadening the class of problems that SATNet architectures can solve to include datasets where no intermediary labels are available at all. We demonstrate that our method allows SATNet to attain full accuracy even with a harder problem setup that prevents any label leakage. We additionally introduce a proofreading method that further improves the performance of SATNet architectures, beating the state-of-the-art on Visual Sudoku.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑