the open
    research
    Contribute
    Back to the reading lists

    Search, retrieval & recommendation· 2005

    Learning to Rank using Gradient Descent

    Christopher J. C. Burges (first author) · 2005

    Read the original

    DOI 10.1145/1102351.1102363OpenAlex W2143331230

    On the reading lists

    Why it matters

    Introduced RankNet, establishing neural pairwise ranking as a practical learning-to-rank approach.

    Condensed from the expert lists' notes.

    Reading it

    Difficulty: Intermediate

    Read this first: neural network basics (backpropagation); information retrieval basics.

    The record

    First released
    2005 (from OpenAlex)
    Citations
    2,805 citations, as counted by OpenAlex (CC0)
    Named by
    both expert lists
    Score
    0.518 · computed rank 218 · consensus 0.76, must-read 1, citations percentile 0.542 (2000s · retrieval), awards 0, existing lists 0. Method

    Editor's notes

    • Readability check: pass: RankNet: pairwise learning to rank, clearly explained. (AI draft (Claude), not yet reviewed, 2026-10-29)

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.