DCGC applies convolution experts and group contrastive learning to improve neural tensor factorization performance on sparse completion tasks in traffic and recommendation data.
arXiv preprint arXiv:2108.04690 (2021)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
AKT-Rec generates semantic IDs via MLLMs and RQ-VAE then applies cluster-guided adaptive embeddings with asymmetric transfer and hierarchical aggregation to improve long-tail recommendation metrics on industrial data.
citing papers explorer
-
Dual-Attention Convolution Experts for Sparse Tensor Completion
DCGC applies convolution experts and group contrastive learning to improve neural tensor factorization performance on sparse completion tasks in traffic and recommendation data.
-
From Head to Tail: Asymmetric Knowledge Transfer in Long-tail Recommendation with Generative Semantic IDs
AKT-Rec generates semantic IDs via MLLMs and RQ-VAE then applies cluster-guided adaptive embeddings with asymmetric transfer and hierarchical aggregation to improve long-tail recommendation metrics on industrial data.