2018

Posthoc Interpretability of Learning to Rank Models using Secondary Training Data

Singh, Jaspreet, Anand, Avishek

Understand

Predictive models are omnipresent in automated and assisted decision making scenarios.

  • But for the most part they are used as black boxes which output a prediction without understanding partially or even completely how different features influence the model prediction avoiding algorithmic transparency.
  • Rankings are ordering over items encoding implicit comparisons typically learned using a family of features using learning-to-rank models.
  • In this paper we focus on how best we can understand the decisions made by a ranker in a post-hoc model agnostic manner.

Built on

  • Adversarial learning

    Lowd, D., and Meek, C · 2005

    Earlier work this paper cites.

  • Ranklib, 2013

    Dang, V · 2013

    Earlier work this paper cites.

  • Introducing LETOR 4.0 datasets

    Original

    Qin, T., and Liu, T · 2013

    Earlier work this paper cites.

Similar

Then

  • The mythos of model interpretability

    Lipton, Z. C · 2016

    Later among the works it cites.

  • Why should i trust you?: Explaining the predictions of any classifier

    Ribeiro, M. T., Singh, S., and Guestrin, C · 2016

    Later among the works it cites.

  • Stochastic gradient boosted distributed decision trees

    Ye, J., Chow, J.-H., Chen, J., and Zheng, Z · 2064

    Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…