KDD

Unleashing the Potential of Neighbors: Diffusion-based Latent Neighbor Generation for Session-based Recommendation

释放邻居的潜力：基于扩散的潜在邻居生成用于基于会话的推荐

Yuhan Yang, Jie Zou, Guojia An, Jiwei Wei, Yang Yang, Heng Tao Shen

AI总结 DiffSBR通过基于扩散的潜在邻居生成方法，提升基于会话的推荐性能。

Comments This paper has been accepted by KDD 2026

TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation

TimeDistill: 通过跨架构知识蒸馏利用MLP实现高效的长期时间序列预测

Juntong Ni, Zewen Liu, Shiyu Wang, Ming Jin, Wei Jin

机构 * Emory University（埃默里大学） ； Griffith University（格里菲斯大学） 纠错

AI总结 TimeDistill通过跨架构知识蒸馏将教师模型的多尺度和多周期模式转移到MLP，显著提升预测性能并降低计算需求

Comments Accepted at KDD 2026, we release our code publicly at https://github.com/LingFengGold/TimeDistill