AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

PRODIGY: Enabling In-context Learning Over Graphs

Qian Huang, Hongyu Ren, Peng Chen, Gregor Kržmanc, Daniel Zeng, Percy Liang, Jure Leskovec

NeurIPS 2023 · Graph learning › Graph self-supervised learning · approach: LLMs and graph foundation models · 6 citations (OpenAlex)

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 changedWhereMeasuredEffect
Remove attribute prediction loss (ablation)PG-NM · arXiv 3-wayaccuracy (%): 65.74 -> 72.50Improved
Remove attribute prediction loss (ablation)PG-NM · arXiv 40-wayaccuracy (%): 18.03 -> 23.69Improved
Remove DropNode and ZeroNode augmentations (ablation)PG-NM · arXiv 3-wayaccuracy (%): 68.98 -> 72.50Improved
Remove both attribute prediction and augmentations (ablation)PG-NM · arXiv 3-wayaccuracy (%): 66.53 -> 72.50Improved
Remove attribute prediction, augmentations and task graph GNN (ablation)PG-NM · arXiv 3-wayaccuracy (%): 63.60 -> 72.50Improved
Reduce neighbor-matching prompt shots from 3 to 1 (ablation)PG-NM · arXiv 3-wayaccuracy (%): 69.13 -> 72.50Improved
Combine neighbor matching and multi-task pretraining (full PRODIGY vs PG-MT)PG-MT · arXiv 3-wayaccuracy (%): 65.64 -> 73.09Improved
Combine neighbor matching and multi-task pretraining (full PRODIGY vs PG-NM)PG-NM · arXiv 40-wayaccuracy (%): 23.69 -> 25.13Improved
Combine both tasks (full PRODIGY vs PG-MT)PG-MT · FB15K-237 5-wayaccuracy (%): 89.15 -> 88.02Mixed
Add contrastive pretraining baseline replaced by PRODIGYContrastive · arXiv 5-wayaccuracy (%): 51.63 -> 61.52Improved
Pretrain with PRODIGY vs pretrain plus finetune headFinetune · arXiv 40-wayaccuracy (%): 8.04 -> 25.13Improved
Compare self-supervised PG-NM to meta-learning TENTTENT · arXiv 3-way test labelsaccuracy (%): 65.13 -> 69.07Improved

Later papers that compared with this method

4 later accepted papers report Prodigy as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy