Research map / Label-efficient and robust learning / Recognition and long-tail
Parallel Neurosymbolic Integration with Concordia
Jonathan Feldstein, Modestas Jurčius, Efthymia Tsamoura
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 |
|---|---|---|---|
| Add the recommendation logic theory to NNMF | NNMF on MovieLens-100k · MovieLens-100k | RMSE: 0.923 -> 0.908 | Improved |
| Add the recommendation logic theory to NeuMF | NeuMF on MovieLens-100k · MovieLens-100k | RMSE: 0.923 -> 0.904 | Improved |
| Add the recommendation logic theory to GraphRec | GraphRec on MovieLens-100k · MovieLens-100k | RMSE: 0.891 -> 0.889 | Improved |
| Add the CAD logic theory to MobileNet | MobileNet on CAAD · CAAD | average accuracy (%): 90.07 -> 90.73 | Improved |
| Add the CAD logic theory to MobileNet | MobileNet on CAAD · CAAD | best accuracy (%): 91.36 -> 93.19 | Improved |
| Add the CAD logic theory to MobileNet | MobileNet on CAAD · CAAD | worst accuracy (%): 89.61 -> 89.54 | Hurt |
| Add the CAD logic theory to Inception | Inception on CAAD · CAAD | average accuracy (%): 89.72 -> 92.75 | Improved |
| Add the CAD logic theory to Inception | Inception on CAAD · CAAD | best accuracy (%): 91.83 -> 93.34 | Improved |
| Add the CAD logic theory to Inception | Inception on CAAD · CAAD | worst accuracy (%): 86.84 -> 92.31 | Improved |
| Add the entity-linking logic theory to Bi-LSTM | Bi-LSTM, unsupervised PubMedParsed · PubMedParsed (unsupervised) | accuracy (%): 70.0 -> 75.8 | Improved |
| Add the entity-linking logic theory to Bi-LSTM | Bi-LSTM, unsupervised PubMedParsed · PubMedParsed (unsupervised) | F1: 0.76 -> 0.78 | Improved |
| Use Concordia with Bi-LSTM instead of supervised Bi-LSTM | Bi-LSTM on PubMedParsed · PubMedParsed (semi-supervised) | accuracy (%): 58.5 -> 80.1 | Improved |
Closest papers by meaning
- DOLPHIN: A Programmable Framework for Scalable Neurosymbolic Learning (ICML 2025 · similarity 0.85)
- Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI (NeurIPS 2025 · similarity 0.85)
- Logically Consistent Language Models via Neuro-Symbolic Integration (ICLR 2025 · similarity 0.84)
- Tensor-Parallelism with Partially Synchronized Activations (NeurIPS 2025 · similarity 0.83)
- CTSketch: Compositional Tensor Sketching for Scalable Neurosymbolic Learning (NeurIPS 2025 · similarity 0.83)
- Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons (AAAI 2024 · similarity 0.83)
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.
