arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.00479cs.LGcs.AI
收藏

通过基于组的子集扫描实现生成模型的创造性表征

Towards creativity characterization of generative models via group-based subset scanning

IBM Research Africa(IBM非洲研究院);IBM Research(IBM研究院)

Celia Cintas, Payel Das, Brian Quanz, Skyler Speakman, Victor Akinwande, Pin-Yu Chen

摘要:

深度生成模型,如变分自编码器(VAE),已被广泛用于计算创造力的研究。然而,这样的模型不鼓励非分布生成以避免虚假样本生成,限制了它们的创造力。因此,将对人类创造力的研究纳入生成式深度学习技术中,可以使其输出更有吸引力,更像人类。当我们看到面向创造力研究的生成模型的出现时,迫切需要基于机器学习的替代指标来表征这些模型的创造性输出。我们提出了基于组的子集扫描,通过检测生成模型的隐藏层中的异常节点激活的子集来量化,检测和表征创造性过程。我们对原始、典型解码和“创造性解码”(Das et al 2020)图像数据集的实验表明,所提出的子集分数分布对于检测激活空间而不是像素空间中的创造性过程更有用。此外,我们发现,在数据集上,创意样本比正常或非创意样本生成更大的异常子集。在创造性解码过程中突出显示的节点激活与负责正常样本生成的节点激活不同。

英文摘要:

Deep generative models, such as Variational Autoencoders (VAEs), have been employed widely in computational creativity research. However, such models discourage out-of-distribution generation to avoid spurious sample generation, limiting their creativity. Thus, incorporating research on human creativity into generative deep learning techniques presents an opportunity to make their outputs more compelling and human-like. As we see the emergence of generative models directed to creativity research, a need for machine learning-based surrogate metrics to characterize creative output from these models is imperative. We propose group-based subset scanning to quantify, detect, and characterize creative processes by detecting a subset of anomalous node-activations in the hidden layers of generative models. Our experiments on original, typically decoded, and "creatively decoded" (Das et al 2020) image datasets reveal that the proposed subset scores distribution is more useful for detecting creative processes in the activation space rather than the pixel space. Further, we found that creative samples generate larger subsets of anomalies than normal or non-creative samples across datasets. The node activations highlighted during the creative decoding process are different from those responsible for normal sample generation.

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。

↑