AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning Multi-Way Relations via Tensor Decomposition With Neural Networks

Koji Maruhashi, Masaru Todoriki, Takuya Ohwa, Keisuke Goto, Yu Hasegawa, Hiroya Inakoshi, Hirokazu Anai

AAAI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 24 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
replace Tucker decomposition with SRTD (ablation)DeepTensor · IDS probingaverage precision: 62.10±5.05 -> 78.52±3.65Improved
replace Tucker decomposition with SRTD (ablation)DeepTensor · IDS DOSaverage precision: 48.75±2.59 -> 62.18±3.56Improved
replace Tucker decomposition with SRTD (ablation)DeepTensor · LENDaverage precision: 4.99±1.15 -> 12.07±1.40Improved
replace Tucker decomposition with SRTD (ablation)DeepTensor · ENZYMESaccuracy: 21.93±0.44 -> 47.17±1.46Improved
learn target core tensor with EBP (vs fixed random) (ablation)DeepTensor · IDS probingaverage precision: 66.16±10.84 -> 78.52±3.65Improved
learn target core tensor with EBP (vs fixed random) (ablation)DeepTensor · IDS DOSaverage precision: 61.00±5.27 -> 62.18±3.56Improved
learn target core tensor with EBP (vs fixed random) (ablation)DeepTensor · LENDaverage precision: 4.78±3.42 -> 12.07±1.40Improved
learn target core tensor with EBP (vs fixed random) (ablation)DeepTensor · ENZYMESaccuracy: 47.07±0.76 -> 47.17±1.46No clear effect
learn target core tensor with EBP (vs fixed random) (ablation)DeepTensor · NCI1accuracy: 75.15±0.41 -> 75.22±0.30No clear effect
add hidden layers to the classifier (ablation)DeepTensor · IDS probingaverage precision: 36.03±5.72 -> 78.52±3.65Improved
add hidden layers to the classifier (ablation)DeepTensor · LENDaverage precision: 10.10±8.51 -> 12.07±1.40Mixed
add hidden layers to the classifier (ablation)DeepTensor · NCI1accuracy: 70.42±0.62 -> 75.22±0.30Improved

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