LoginSignup
3
1

More than 1 year has passed since last update.

推薦システムのトレンド

Posted at

目的

推薦システムやIRのトレンドについて調べたので結果をまとめておく

  • Recent Trends in Personalization: A Netflix Perspective
    • 2019年時点
  • 言語モデル関連
    • 自然言語処理の分野で巨大な言語モデルが諸々のタスクで凄まじいパフォーマンスを出せることが分かった
    • 言語モデルのパワーを推薦や情報検索(IR)に使いたい!
    • Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation of BERT Rankers (SIGIR 2021)
    • Leveraging Lead Bias for Zero-shot Abstractive News Summarization (SIGIR 2021)
    • Can Language Models Identify Wikipedia Articles with Readability and Style Issues? (ICTIR21)
  • 反実仮想関連
    • データが得られたのってすごい狭い過去ですよね?
    • Counterfactual Data-Augmented Sequential Recommendation (SIGIR 2021)
    • CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation (SIGIR 2021)
  • bias
    • データから学習させる時にデータのbiasをどう対処していくか?
    • Causal Intervention for Leveraging Popularity Bias in Recommendation (SIGIR 2021)
    • Popularity-Opportunity Bias in Collaborative Filtering (WSDM 2021)
  • grash構造の活用
    • 知識グラフを使うことで推薦がよりよくなる
    • Diagnosis Ranking with Knowledge Graph Convolutional Networks (ECIR 2021)
    • An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph (KDD 2020)
    • Attentional Graph Convolutional Networks for Knowledge Concept Recommendation in MOOCs in a Heterogeneous View(SIGIR 2020)
  • 説明性
    • 推薦の理由を知りたい
    • Interpretable Ranking with Generalized Additive Models (WSDM 2021)
    • Towards Axiomatic Explanations for Neural Ranking Models (ICTIR 2021)
3
1
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
3
1