Corpus ID: 196471193

Learning Functions over Sets via Permutation Adversarial Networks

@article{Pabbaraju2019LearningFO,
  title={Learning Functions over Sets via Permutation Adversarial Networks},
  author={Chirag Pabbaraju and Prateek Jain},
  journal={ArXiv},
  year={2019},
  volume={abs/1907.05638}
}
  • Chirag Pabbaraju, Prateek Jain
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • In this paper, we consider the problem of learning functions over sets, i.e., functions that are invariant to permutations of input set items. Recent approaches of pooling individual element embeddings can necessitate extremely large embedding sizes for challenging functions. We address this challenge by allowing standard neural networks like LSTMs to succinctly capture the function over the set. However, to ensure invariance with respect to permutations of set elements, we propose a novel… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 34 REFERENCES

    Learning Representations of Sets through Optimized Permutations

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Deep Sets

    DeepPermNet: Visual Permutation Learning

    VIEW 1 EXCERPT

    Generative Adversarial Nets

    VIEW 1 EXCERPT

    Adam: A Method for Stochastic Optimization

    VIEW 1 EXCERPT

    DeepSetNet: Predicting Sets with Deep Neural Networks

    VIEW 1 EXCERPT

    Ranking via Sinkhorn Propagation

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL