AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Learning Graph Embeddings for Open World Compositional Zero-Shot Learning

Massimiliano Mancini, Muhammad Ferjad Naeem, Yongqin Xian, Zeynep Akata

TPAMI 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 102 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
add self-connections for composition nodes in the graph (ablation)CGE graph · MIT-States val (closed world)AUC: 7.6 -> 8.1Improved
add state-object links to the graph (ablation)CGE graph · MIT-States val (closed world)AUC: 8.1 -> 8.6Improved
replace dot-product classifier with cosine classifier (ablation)CGE · MIT-States val (closed world)AUC: 8.6 -> 7.9No clear effect
include all unseen compositions in the loss without margin (ablation)CompCos · MIT-States val (open world)AUC: 1.2 -> 1.7Improved
add feasibility margin alpha>0 (ablation)CompCos · MIT-States val (open world)AUC: 1.7 -> 2.0Improved
linearly warm up alpha (ablation)CompCos · MIT-States val (open world)AUC: 2.0 -> 2.1Improved
average state and object feasibility instead of max (ablation)CompCos · MIT-States val (open world)AUC: 2.0 -> 2.1Improved
keep composition-to-primitive graph weights at 1 instead of feasibility (ablation)Co-CGE_ff · MIT-States val (open world)AUC: average improvement of 0.63 in AUCImproved
weight s-o and p-c graph links by feasibility (ablation)Co-CGE_ff · MIT-States val (open world)AUC: 2.4 -> 2.5Improved
fine-tune end-to-end rather than frozen features (ablation)Co-CGE · MIT-States val (open world)AUC: 2.5 -> 2.8Improved
compute feasibility from primitive similarity to training neighbours instead of direct state-object similarity (ablation)Co-CGE · MIT-States val (open world)AUC: 1.7 vs 2.5 in AUCImproved
use cosine similarity instead of Euclidean distance for feasibility (ablation)Co-CGE · MIT-States val (open world)AUC: 2.5 AUC on Ours vs 1.4 of Exp. Euclidean and 1.1 of EuclideanImproved

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