IJCAI 2021poster7 citations

Temporal and Object Quantification Networks

Jiayuan Mao, Zhezheng Luo, Chuang Gan, Joshua B. Tenenbaum, Jiajun Wu, Leslie Pack Kaelbling, Tomer D. Ullman

Abstract

We present Temporal and Object Quantification Networks (TOQ-Nets), a new class of neuro-symbolic networks with a structural bias that enables them to learn to recognize complex relational-temporal events. This is done by including reasoning layers that implement finite-domain quantification over objects and time. The structure allows them to generalize directly to input instances with varying numbers of objects in temporal sequences of varying lengths. We evaluate TOQ-Nets on input domains that require recognizing event-types in terms of complex temporal relational patterns. We demonstrate that TOQ-Nets can generalize from small amounts of data to scenarios containing more objects than were present during training and to temporal warpings of input sequences.

Machine Learning: Neuro-Symbolic MethodsMachine Learning: Relational Learning
BibTeX
@inproceedings{ijcai2021p386,
  title     = {Temporal and Object Quantification Networks},
  author    = {Mao, Jiayuan and Luo, Zhezheng and Gan, Chuang and Tenenbaum, Joshua B. and Wu, Jiajun and Kaelbling, Leslie Pack and Ullman, Tomer D.},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Zhi-Hua Zhou},
  pages     = {2804--2811},
  year      = {2021},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2021/386},
  url       = {https://doi.org/10.24963/ijcai.2021/386},
}
Temporal and Object Quantification Networks · IJCAI 2021