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
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 |
|---|---|---|---|
| replace original transductive QE with inductive IQE as target for the feature map | Phi(.) feature map · FIGER test | Accuracy: 0.383 -> 0.631 | Improved |
| replace original QE with IQE as target for the feature map | Phi(.) feature map · FIGER test | Macro F1: 0.420 -> 0.764 | Improved |
| replace original QE with IQE as target for the feature map | Phi(.) feature map · FIGER test | Micro F1: 0.347 -> 0.724 | Improved |
| use IQE instead of strongest baseline Attentive | FgETC classifier · FIGER test | Accuracy: 0.589 -> 0.631 | Improved |
| use IQE instead of strongest baseline Attentive | FgETC classifier · FIGER test | Macro F1: 0.779 -> 0.764 | Hurt |
| use IQE instead of strongest baseline Attentive | FgETC classifier · FIGER test | Micro F1: 0.749 -> 0.724 | Hurt |
| use IQE instead of AFET | FgETC classifier · FIGER test | Accuracy: 0.533 -> 0.631 | Improved |
| alternating faster training scheme instead of SGD-based original QE scheme | QE training · FIGER | QE generation time (Tqe): 27800.0 -> 3063.6 | Improved |
| alternating scheme instead of original SGD scheme, including feature map training | QE pipeline · FIGER | total time (Tqe + Tnn): 35450.0 -> 10713.6 | Improved |
| alternating scheme instead of original scheme | QE training · FIGER | per-iteration time tqe: 27.8 -> 510.6 | Hurt |
| alternating scheme instead of original scheme | QE training · FIGER | number of iterations: 1000 -> 6 | Improved |
Closest papers by meaning
- Quantum Embedding of Knowledge for Reasoning (NeurIPS 2019 · similarity 0.89)
- Faithful Embeddings for Knowledge Base Queries (NeurIPS 2020 · similarity 0.88)
- QuanTaxo: A Quantum Approach to Self-Supervised Taxonomy Expansion (AAAI 2026 · similarity 0.84)
- Enriching Disentanglement: From Logical Definitions to Quantitative Metrics (NeurIPS 2024 · similarity 0.83)
- An Evaluation of Approaches to Train Embeddings for Logical Inference (Student Abstract) (AAAI 2025 · similarity 0.83)
- Improving Soft Unification with Knowledge Graph Embedding Methods (ICML 2025 · similarity 0.82)
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.
