[
  {
    "id": "dl-15-1",
    "type": "article",
    "title": "Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer",
    "author": [
      {
        "given": "Noam",
        "family": "Shazeer"
      },
      {
        "given": "Azalia",
        "family": "Mirhoseini"
      },
      {
        "given": "Krzysztof",
        "family": "Maziarz"
      },
      {
        "given": "Andy",
        "family": "Davis"
      },
      {
        "given": "Quoc",
        "family": "Le"
      },
      {
        "given": "Geoffrey",
        "family": "Hinton"
      },
      {
        "given": "Jeff",
        "family": "Dean"
      }
    ],
    "container-title": "arXiv preprint",
    "issued": {
      "date-parts": [
        [
          2017
        ]
      ]
    },
    "DOI": "10.48550/arXiv.1701.06538",
    "URL": "https://arxiv.org/abs/1701.06538"
  },
  {
    "id": "dl-15-2",
    "type": "article-journal",
    "title": "Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity",
    "author": [
      {
        "given": "William",
        "family": "Fedus"
      },
      {
        "given": "Barret",
        "family": "Zoph"
      },
      {
        "given": "Noam",
        "family": "Shazeer"
      }
    ],
    "container-title": "Journal of Machine Learning Research, 23(120):1-39",
    "issued": {
      "date-parts": [
        [
          2022
        ]
      ]
    },
    "DOI": "",
    "URL": "https://jmlr.org/papers/v23/21-0998.html"
  },
  {
    "id": "dl-15-3",
    "type": "article",
    "title": "GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding",
    "author": [
      {
        "given": "Dmitry",
        "family": "Lepikhin"
      },
      {
        "given": "HyoukJoong",
        "family": "Lee"
      },
      {
        "given": "Yuanzhong",
        "family": "Xu"
      },
      {
        "given": "Dehao",
        "family": "Chen"
      },
      {
        "given": "Orhan",
        "family": "Firat"
      },
      {
        "given": "Yanping",
        "family": "Huang"
      },
      {
        "given": "Maxim",
        "family": "Krikun"
      },
      {
        "given": "Noam",
        "family": "Shazeer"
      },
      {
        "given": "Zhifeng",
        "family": "Chen"
      }
    ],
    "container-title": "arXiv preprint",
    "issued": {
      "date-parts": [
        [
          2020
        ]
      ]
    },
    "DOI": "10.48550/arXiv.2006.16668",
    "URL": "https://arxiv.org/abs/2006.16668"
  }
]