AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Inductive Quantum Embedding

Santosh Kumar Srivastava, Dinesh Khandelwal, Dhiraj Madan, Dinesh Garg, Hima Karanam, L Venkata Subramaniam

NeurIPS 2020 · Architectures and efficiency › RNNs and normalization · approach: Learned embeddings for retrieval · 1 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 original transductive QE with inductive IQE as target for the feature mapPhi(.) feature map · FIGER testAccuracy: 0.383 -> 0.631Improved
replace original QE with IQE as target for the feature mapPhi(.) feature map · FIGER testMacro F1: 0.420 -> 0.764Improved
replace original QE with IQE as target for the feature mapPhi(.) feature map · FIGER testMicro F1: 0.347 -> 0.724Improved
use IQE instead of strongest baseline AttentiveFgETC classifier · FIGER testAccuracy: 0.589 -> 0.631Improved
use IQE instead of strongest baseline AttentiveFgETC classifier · FIGER testMacro F1: 0.779 -> 0.764Hurt
use IQE instead of strongest baseline AttentiveFgETC classifier · FIGER testMicro F1: 0.749 -> 0.724Hurt
use IQE instead of AFETFgETC classifier · FIGER testAccuracy: 0.533 -> 0.631Improved
alternating faster training scheme instead of SGD-based original QE schemeQE training · FIGERQE generation time (Tqe): 27800.0 -> 3063.6Improved
alternating scheme instead of original SGD scheme, including feature map trainingQE pipeline · FIGERtotal time (Tqe + Tnn): 35450.0 -> 10713.6Improved
alternating scheme instead of original schemeQE training · FIGERper-iteration time tqe: 27.8 -> 510.6Hurt
alternating scheme instead of original schemeQE training · FIGERnumber of iterations: 1000 -> 6Improved

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