Research map / Label-efficient and robust learning / Recognition and long-tail
Learning and Interpreting Multi-Multi-Instance Learning Networks
Alessandro Tibo, Manfred Jaeger, Paolo Frasconi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| represent IMDB reviews as bags of sentences (MMIL) instead of a flat bag of trigrams (MIL) | bag-layer network · IMDB sentiment | accuracy (%): 91.41 -> 92.18 | Improved |
| use nested MMIL structure for rule distillation instead of MIL | IMDB rule model · IMDB sentiment (extracted rules) | accuracy (%): 86.37 -> 87.49 | Improved |
| use nested MMIL structure for rule distillation instead of MIL | IMDB rule model · IMDB sentiment (extracted rules) | fidelity (%): 88.10 -> 90.40 | Improved |
| use nested MMIL structure for rule distillation instead of MIL | PubMed rule model · PubMed (extracted rules) | accuracy (%): 79.25 -> 76.88 | Hurt |
| distill the MMIL network into rules | MMIL network · Semi-synthetic MNIST MMIL (test) | accuracy (%): 98.42 -> 98.18 | No clear effect |
Closest papers by meaning
- Drawer Graph Neural Network for Multi-Instance Learning (TPAMI 2026 · similarity 0.89)
- Bag Graph: Multiple Instance Learning Using Bayesian Graph Neural Networks (AAAI 2022 · similarity 0.89)
- Robust Self-Supervised Multi-Instance Learning with Structure Awareness (AAAI 2023 · similarity 0.88)
- Multi-View Multi-Instance Learning Based on Joint Sparse Representation and Multi-View Dictionary Learning (TPAMI 2017 · similarity 0.86)
- Multiple-Instance Learning from Distributions (JMLR 2016 · similarity 0.86)
- Equivalence is All: A Unified View for Self-supervised Graph Learning (ICML 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
