Research map / Graph learning / Knowledge and temporal graphs
Probabilistic Logic Neural Networks for Reasoning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 MLN logic rules to TransE (pLogicNet*) | TransE · FB15k | MRR: 0.730 -> 0.844 | Helped |
| add MLN logic rules to TransE (pLogicNet*) | TransE · WN18RR | MRR: 0.223 -> 0.441 | Helped |
| add MLN logic rules to TransE (pLogicNet*) | TransE · FB15k-237 | MRR: 0.326 -> 0.332 | Helped |
| combine q_theta and p_w at inference (pLogicNet*) instead of q_theta only (ablation) | pLogicNet · WN18 | MRR: 0.832 -> 0.945 | Helped |
| combine q_theta and p_w at inference (pLogicNet*) instead of q_theta only (ablation) | pLogicNet · FB15k-237 | H@10: 52.8 -> 52.4 | Hurt |
| add inverse rules (ablation) | pLogicNet (TransE) · FB15k | MRR: 0.730 -> 0.813 | Helped |
| add composition rules (ablation) | pLogicNet (TransE) · FB15k | H@3: 79.4 -> 78.7 | Hurt |
| add composition rules (ablation) | pLogicNet (TransE) · FB15k-237 | MRR: 0.326 -> 0.335 | Helped |
| add symmetric rules (ablation) | pLogicNet (TransE) · FB15k | MRR: 0.730 -> 0.793 | Helped |
| add subrelation rules (ablation) | pLogicNet (TransE) · FB15k | MRR: 0.730 -> 0.761 | Helped |
| use ComplEx instead of TransE as KGE (ablation) | pLogicNet* · WN18RR | MRR: 0.441 -> 0.475 | Helped |
| use ComplEx instead of TransE as KGE (ablation) | pLogicNet* · FB15k | MRR: 0.844 -> 0.788 | Hurt |
Closest papers by meaning
- Efficient Probabilistic Logic Reasoning with Graph Neural Networks (ICLR 2020 · similarity 0.93)
- RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs (ICLR 2021 · similarity 0.89)
- Differentiable Neuro-Symbolic Reasoning on Large-Scale Knowledge Graphs (NeurIPS 2023 · similarity 0.89)
- Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors (ICLR 2024 · similarity 0.87)
- Systematic Relational Reasoning With Epistemic Graph Neural Networks (ICLR 2025 · similarity 0.85)
- Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning (AAAI 2025 · similarity 0.85)
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.