TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MAGNET

MAGNET

Reported on 18 benchmarks across 4 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology11 results

  • Multi-Label Text ClassificationonAAPD
    F1
    69.6
  • Multi-Label Text ClassificationonSlashdot
    Micro-F1
    56.8
  • Multi-Label Text ClassificationonRCV1-v2
    Micro-F1
    88.5
  • Multi-Label Text ClassificationonReuters-21578
    Micro-F1
    89.9
    best: 90.74 (CB-NTR)
  • ClassificationonRCV1
    Micro F1
    88.5
  • ClassificationonReuters-21578
    F1
    89.9
  • ClassificationonAAPD
    F1
    69.6
    best: 72.9 (KD-LSTMreg)
  • ClassificationonAAPD
    F1
    69.6
    best: 72.9 (KD-LSTMreg)
  • ClassificationonSlashdot
    Micro-F1
    56.8
  • ClassificationonRCV1-v2
    Micro-F1
    88.5
  • ClassificationonReuters-21578
    Micro-F1
    89.9
    best: 90.74 (CB-NTR)

Natural Language Processing9 results

  • Text ClassificationonRCV1
    Micro F1
    88.5
  • Text ClassificationonReuters-21578
    F1
    89.9
  • Text ClassificationonAAPD
    F1
    69.6
    best: 72.9 (KD-LSTMreg)
  • Text ClassificationonAAPD
    F1
    69.6
    best: 72.9 (KD-LSTMreg)
  • Text ClassificationonSlashdot
    Micro-F1
    56.8
  • Text ClassificationonRCV1-v2
    Micro-F1
    88.5
  • Text ClassificationonReuters-21578
    Micro-F1
    89.9
    best: 90.74 (CB-NTR)
  • Document ClassificationonReuters-21578
    F1
    89.9
  • Document ClassificationonAAPD
    F1
    69.6
    best: 72.9 (KD-LSTMreg)