Research map / Label-efficient and robust learning / Recognition and long-tail
Learning with Holographic Reduced Representations
Ashwinkumar Ganesan, Hang Gao, Sunil Gandhi, Edward Raff, Tim Oates, James Holt, Mark McLean
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 the fully-connected output layer with the HRR dense label output | FC · Bibtex | P@1: 46.4 -> 60.3 | Improved |
| replace the fully-connected output layer with the HRR dense label output | FC · Delicious-200K | P@1: 21.8 -> 44.9 | Improved |
| replace the fully-connected output layer with the HRR dense label output | FC · Delicious-200K | PSP@1: 10.5 -> 6.84 | Hurt |
| replace the fully-connected output layer with the HRR dense label output | CNN · Wiki10-31K | P@1: 60.0 -> 74.3 | Improved |
| replace the fully-connected output layer with the HRR dense label output | LSTM · EURLex-4K | P@1: 63.0 -> 70.4 | Improved |
| replace the fully-connected output layer with the HRR dense label output | CNN · Amazon-12K | P@1: 89.1 -> 84.5 | Hurt |
| replace the fully-connected output layer with the HRR dense label output | FC · Amazon-670K | P@1: 34.6 -> 19.9 | Hurt |
| replace the fully-connected output layer with the HRR dense label output | FC · Amazon-670K | PSP@1: 5.22 -> 8.45 | Improved |
| replace the fully-connected output layer with the HRR dense label output | FC · Amazon-670K | training time speedup: 6.28 | Improved |
| replace the fully-connected output layer with the HRR dense label output | FC · Bibtex | training time speedup: 0.35 | Hurt |
| make baseline FC deeper (2 to 3 layers, h=512) (ablation) | FC · Wiki10-31K | P@5: 46.64 -> 41.92 | Hurt |
| increase HRR output dimension d' and network size (h=512,d'=400 to 3 layers h=2048,d'=3000) (ablation) | HRR-FC · Wiki10-31K | P@5: 55.06 -> 58.51 | Improved |
Closest papers by meaning
- SINR: Sparsity Driven Compressed Implicit Neural Representations (CVPR 2025 · similarity 0.84)
- Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length (ICLR 2025 · similarity 0.82)
- ReLUs Are Sufficient for Learning Implicit Neural Representations (ICML 2024 · similarity 0.82)
- Implicit Neural Representations and the Algebra of Complex Wavelets (ICLR 2024 · similarity 0.81)
- Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning (NeurIPS 2026 · similarity 0.81)
- Combining Frame and GOP Embeddings for Neural Video Representation (CVPR 2024 · similarity 0.81)
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.
