arXiv Machine Learning
FlowNeg: GFlowNet-Guided Diverse Hard Negative Sampling for Knowledge Graph Embedding
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
Hugging Face Trending Papers
Aug 24
FlowNeg: GFlowNet-Guided Diverse Hard Negative Sampling for Knowledge Graph Embedding
Negative sampling determines whether a knowledge graph embedding (KGE) model learns from informative counterexamples or wastes updates on implausible corruptions. Uniform negatives are diverse but eas...
arXiv AI
4d ago
CA-HNM: Constraint-Aware Hard Negative Mining for Dense Retrieval with Structured Domain Models
arXiv:2610.35045v1 Announce Type: cross Abstract: Dense retrievers are commonly trained with hard negatives selected from lexical or dense retrieval results. Retrieval proximity, however, does not in...
arXiv AI
Jun 16
Boosting Knowledge Graph Foundation Models via Enhanced Negative Sampling
arXiv:2605. 27023v2 Announce Type: replace Abstract: Knowledge graphs (KGs) have become the core backbone of numerous downstream tasks such as question answering and recommender systems.
arXiv AI
Sep 1
PyKEEN-NSX: A Modular Framework for Static, Dynamic and Schema-Aware Negative Sampling in PyKEEN
arXiv:2608.30652v1 Announce Type: new Abstract: Embedding methods have become popular due to their scalability on link prediction and/or triple classification tasks on Knowledge Graphs (KGs). Embeddi...
arXiv AI
Jul 24
Mean-to-Score Discrete Diffusion: Posterior-Mean Denoisers for Score Entropy
arXiv:2607. 21372v1 Announce Type: cross Abstract: Score Entropy Discrete Diffusion (SEDD) parameterizes discrete reverse processes with unconstrained positive score ratios.
Hugging Face Trending Papers
Jul 23
Mean-to-Score Discrete Diffusion: Posterior-Mean Denoisers for Score Entropy
Score Entropy Discrete Diffusion (SEDD) parameterizes discrete reverse processes with unconstrained positive score ratios. While positivity guarantees nonnegative reverse jump rates, it does not ensure Bayes realizability: ratios at a noisy state need not be jointly induced by any clean-token posterior under the forward kernel.