Research map / Probabilistic and scientific modeling / Molecules and proteins
Predicting Links in Plant-Pollinator Interaction Networks Using Latent Factor Models With Implicit Feedback
Eugene Seo, Rebecca Hutchinson
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 |
|---|---|---|---|
| Use matrix-based availability (A.mat) instead of vector-based (A.vec) (ablation) | IFMF2 · 2011 new interactions | MPR (mean percentile rank): 23.47 -> 13.10 | Improved |
| A.mat instead of A.vec (ablation) | IFMF2 · 2011 all interactions | MPR (mean percentile rank): 15.36 -> 9.33 | Improved |
| A.mat instead of A.vec (ablation) | IFMF2 · 2013 all interactions | MPR (mean percentile rank): 20.12 -> 19.50 | No clear effect |
| A.mat instead of A.vec (ablation) | IFMF · 2012 all interactions | MPR (mean percentile rank): 15.44 -> 17.13 | Hurt |
| A.mat instead of A.vec (ablation) | IFMF · 2014 new interactions | MPR (mean percentile rank): 20.84 -> 22.85 | Hurt |
| Add negative implicit feedback (IFMF2 vs IFMF), A.mat (ablation) | IFMF · 2012 new interactions | MPR (mean percentile rank): 16.67 -> 13.10 | Improved |
| Add implicit feedback to MF (IFMF vs MF), A.vec | MF · 2011 new interactions | MPR (mean percentile rank): 23.55 -> 23.48 | Improved |
| Add implicit feedback to MF (IFMF vs MF), A.vec | MF · 2015 new interactions | MPR (mean percentile rank): 42.11 -> 29.24 | Improved |
| Use IFMF2 instead of Popularity baseline | Popularity · 2011 all interactions | MPR (mean percentile rank): 10.29 -> 15.36 | Hurt |
| Use IFMF2 instead of Popularity baseline | Popularity · 2012 new interactions | MPR (mean percentile rank): 22.28 -> 23.47 | Hurt |
| Use IFMF2 with A.mat instead of Popularity with A.mat | Popularity · 2012 new interactions | MPR (mean percentile rank): 16.52 -> 13.10 | Improved |
| Use Availability baseline instead of Popularity | Popularity · 2011 all interactions | MPR (mean percentile rank): 10.29 -> 27.54 | Hurt |
Closest papers by meaning
- Dispatch Guided Allocation Optimization for Effective Emergency Response (AAAI 2018 · similarity 0.98)
- Variational Inference for sparse network reconstruction from count data (ICML 2019 · similarity 0.82)
- Nonparametric Network Models for Link Prediction (JMLR 2016 · similarity 0.82)
- Oxytrees: Model Trees for Bipartite Learning (AAAI 2026 · similarity 0.82)
- Harnessing Multiple Correlated Networks for Exact Community Recovery (NeurIPS 2024 · similarity 0.81)
- PhyloGFN: Phylogenetic inference with generative flow networks (ICLR 2024 · similarity 0.80)
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.
