- 综合排序
- 最热优先
- 最新优先
- 来自专栏机器学习与推荐算法
SIGIR2020推荐系统论文聚焦
为了方便查看与了解，我们主要将其分为了以下几类：Sequential RS，Graph-based RS，Cold-start in RS，Efficient RS，Knowledge-aware RS 分类 数量 Sequential RS 8 Graph-based RS 6 Robust RS 6 Efficient RS 5 Knowledge-aware RS 5 Cold-start in Cold-start RS Content-aware Neural Hashing for Cold-start Recommendation. Recommending Podcasts for Cold-Start Users Based on Music Listening and Taste. CATN: Cross-Domain Recommendation for Cold-Start Users via Aspect Transfer Network.
2.2K31发布于 2020-06-17 - 来自专栏机器学习与推荐算法
SIGIR 2021 | 推荐系统相关论文分类整理
in Recommender System Learning Graph Meta Embeddings for Cold-Start Ads in Click-Through Rate Prediction 【学习图元嵌入表示】 FORM: Follow the Online Regularized Meta-Leader for Cold-Start Recommendation【在线正则化的元学习器】 for Cold-start Recommendation with Meta Scaling and Shifting Networks【如何warm up】 Fairness among New Users【short paper】 Cluster-Based Bandits: Fast Cold-Start for Recommender System New Users【short paper ，基于聚类的老虎机模型来快速冷启动】 Sequential Recommendation for Cold-start Users with Meta Transitional Learning【short
1.7K40发布于 2021-05-11 - 来自专栏圆圆的算法笔记
盘点5类推荐系统中图学习解决冷启动问题的方法
1 融合邻居节点预训练表示 Learning Graph Meta Embeddings for Cold-Start Ads in Click-Through Rate Prediction（SIGIR Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation（WSDM 2021）中也提出了类似的方法 Hers: Modeling influential contexts with heterogeneous relations for sparse and cold-start recommendation 例如在GIFT: Graph-guIded Feature Transfer for Cold-Start Video Click-Through Rate Prediction（CIKM 2022）这篇文章中 Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation（WSDM 2021）中通过也引入了user
1.5K10编辑于 2022-12-19 - 来自专栏机器学习与推荐算法
一文梳理冷启动推荐算法模型进展
[2] Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings IJCAI2017. [6] Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users. KDD2021. [9] A Meta-Learning Perspective on Cold-Start Recommendations for Items. NeurIPS2017. [10] MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation. KDD2019. [11] Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation.
2.3K40发布于 2021-08-06 - 来自专栏AI科技评论
WSDM 2022 | 中科院、腾讯、北航提出：跨领域推荐中的个性化迁移用户兴趣偏好
warm start实验，也就是基于这个映射得到向量表示作为初始化，使用后续交互数据微调，得到以下结果，可以看到，针对warm start场景，我们的方法也是很有效的，这也是第一篇同时验证跨领域推荐方法在cold-start Semi-supervised learning for cross-domain recommendation to cold-start users[C]// CIKM: 1563-1572. [3 Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users[C]. Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting
1K20发布于 2021-11-05 - 来自专栏AI科技评论
中科院、腾讯、北航合作：基于元学习实现更好的冷启动推荐 | SIGIR 2021
本文基于SIGIR-2021论文《Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling 在这篇文章中，我们将冷启动问题划分为两个阶段，cold-start阶段和warm-up阶段，cold-start阶段表示完全没有样本的情况，而warm-up阶段表示有少量样本的情况。 Warm up cold-start advertisements: Improving ctr predictions via learning to learn id embeddings[C]// MeLU: meta-learned user preference estimator for cold-start recommendation[C]//Proceedings of the 25th
1.5K30发布于 2021-07-02 - 来自专栏AI前沿技术
Deepseek-R1 训练过程，两步四阶段，一图搞定！
目标：1) 使RL训练的前期阶段变得稳定，2)进一步增强推理能力 cold-start 数据构成： 类型：长cot高质量，可读性强且人工double-check数据 量级：千级别 来源：DeepSeek-R1 • 通过在进行RL之前，进行cold-start的监智学习，可以得到解决! 此时的模型，已经具有了很强的推理能力，且可读性ok，多语言混杂的问题也已经基本解决。 获得模型：满血版 DeepSeek-R1 3，总结 阶段 作用 数据 stage1-SFT 稳定RL过程，增强可读性，解决多语言问题 千级别cold-start stage2-RL 获得涌现的推理能力
46510编辑于 2026-01-13 - 来自专栏机器学习与推荐算法
CIKM2021推荐系统论文集锦
Simulation Counterfactual Review-based Recommendation Reinforcement Learning to Optimize Lifetime Value in Cold-Start Recommendation Zero Shot on the Cold-Start Problem: Model-Agnostic Interest Learning for Recommender Meta-learning Model for Session-based Recommendation CMML: Contextual Modulation Meta Learning for Cold-Start
96520发布于 2021-10-27 - 来自专栏海边的拾遗者
推荐算法最前沿 | KDD 2020推荐算法论文一览（内附下载链接）
Geography-Aware Sequential Location Recommendation 【Microsoft】 论文：staff.ustc.edu.cn/~lian Cold-Start MAMO: Memory-Augmented Meta-Optimization for Cold-start Recommendation 论文：arxiv.org/abs/2007.0318 2. Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation 论文：https://ink.library.smu.edu.sg
3.1K32发布于 2020-11-17 - 来自专栏对白的算法屋
SIGIR 2022 | 推荐系统相关论文分类整理
AutoML-based Others 3 按照研究话题划分 Bias/Debias in Recommender System Explanation in Recommender System Long-tail/Cold-start in Recommender System Socially-aware Dual Contrastive Learning for Cold-Start Recommendation 【short paper，社交感知的双重对比学习】 Transform Cold-Start Users into Warm via Fused Behaviors in Large-Scale Recommendation 【short paper，通过融合行为转换冷启动用户】 Generative Adversarial Framework for Cold-Start Item Recommendation 【short paper，针对冷启动商品的生成对抗框架】 Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational
1.9K10编辑于 2022-05-17 - 来自专栏机器学习与推荐算法
AAAI2022推荐系统论文集锦
A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations Krishna P Neupane, Ervine SMINet: State-Aware Multi-Aspect Interests Representation Network for Cold-Start Users Recommendation
1.2K40编辑于 2022-02-28 - 来自专栏圆圆的算法笔记
数据稀疏如何学好embedding？
第二篇文章是Learning to warm up cold item embeddings for cold-start recommendation with meta scaling and shifting 在今年的SIGIR上，Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational Autoencoder 3 基于对比学习学习embedding 基于对比学习学习embedding的典型工作是Contrastive learning for cold-start recommendation（Multimedia 4 根据用户历史行为生成embedding 在今年SIGIR 2022中阿里发表了一篇文章Transform Cold-Start Users into Warm via Fused Behaviors
1.4K10编辑于 2022-12-19 - 来自专栏机器学习与推荐算法
SIGIR2023推荐系统论文集锦
A Preference Learning Decoupling Framework for User Cold-Start Recommendation Chunyang Wang, Yanmin Zhu Model-agnostic Behavioral Distillation For Cold-start Item Recommendation Zefan Wang, Hao Chen, Xiao M2EU: Meta Learning for Cold-start Recommendation via Enhancing User Preference Estimation Zhenchao Wu Uncertainty-aware Consistency Learning for Cold-Start Item Recommendation Taichi Liu, Chen Gao, Zhenyu TAML: Time-Aware Meta Learning for Cold-Start Problem in News Recommendation Jingyuan Li, Yue Zhang,
1.8K10编辑于 2023-08-22 - 来自专栏AI科技评论
动态 | ACL 2018 公布四篇最佳 demo 候选论文，三篇论文第一作者来自中国
雷锋网 AI 科技评论按：7 月 9 日，自然语言处理顶会 ACL 公布了最佳 demo 论文的四篇候选论文，名单如下： CRUISE: Cold-Start New Skill Development 最佳 demo 论文 CRUISE: Cold-Start New Skill Development via Iterative Utterance Generation CRUISE：基于迭代语料生成的冷启动新技能开发
59040发布于 2018-07-27 - 来自专栏机器学习与推荐算法
CIKM2022推荐系统论文集锦
Prediction Framework for Imbalanced Recommendation Generative Adversarial Zero-Shot Learning for Cold-Start Multi-Faceted Hierarchical Multi-Task Learning for Recommender Systems Multimodal Meta-Learning for Cold-Start
1.2K30编辑于 2022-10-31 - 来自专栏秋枫学习笔记
CIKM 2022 推荐系统，因果推断论文整理
Imbalanced Recommendation【GRP：基于 Gumbel 的不平衡推荐评级预测框架】 Generative Adversarial Zero-Shot Learning for Cold-Start Contrastive Learning Framework for Sequential Recommendation【序列推荐的多层次对比学习框架】 Multimodal Meta-Learning for Cold-Start User Recommendation in Social Metaverse with VR【VR的用户推荐】 点击率估计 GIFT: Graph-guIded Feature Transfer for Cold-Start
1.4K40编辑于 2023-01-30 - 来自专栏圆圆的算法笔记
长尾预测效果不好怎么办？试试这两种思路
第二篇文章是MeLU: meta-learned user preference estimator for cold-start recommendation（KDD 2019）。 Learning Graph Meta Embeddings for Cold-Start Ads in Click-Through Rate Prediction（SIGIR 2021）利用图学习解决新
1.5K20编辑于 2022-12-19 - 来自专栏机器学习与推荐算法
论文周报 | 推荐系统领域最新研究进展，含KDD, SIGIR, UAI等顶会论文
ColdNAS: Search to Modulate for User Cold-Start Recommendation 9. ColdNAS: Search to Modulate for User Cold-Start Recommendation Shiguang Wu, Yaqing Wang, Qinghe Jing, Dong, Dejing Dou, Quanming Yao https://arxiv.org/abs/2306.03387 Making personalized recommendation for cold-start deciding modulation position by expertise, we propose a modulation framework called ColdNAS for user cold-start that JGCF is better at handling sparse datasets, which shows potential in making recommendations for cold-start
1.2K11编辑于 2023-08-22 - 来自专栏机器学习与推荐算法
论文周报 | 推荐系统领域最新研究进展，含WWW、ICDE、CIKM等顶会论文
CoMeta: Enhancing Meta Embeddings with Collaborative Information in Cold-start Problem of Recommendation CoMeta: Enhancing Meta Embeddings with Collaborative Information in Cold-start Problem of Recommendation Haonan Hu, Dazhong Rong, Jianhai Chen, Qinming He, Zhenguang Liu https://arxiv.org/abs/2303.07607 The cold-start Some recent studies introduce meta learning to solve the cold-start problem by generating meta embeddings
77820编辑于 2023-08-22 - 来自专栏机器学习与推荐算法
一文梳理跨域推荐研究进展
IJCAI2017. [3] Semi-supervised learning for cross-domain recommendation to cold-start users. CIKM2019. [4] Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users.
2K30发布于 2021-09-23
腾讯云开发者
Copyright © 2013 - 2026 Tencent Cloud. All Rights Reserved. 腾讯云 版权所有
深圳市腾讯计算机系统有限公司 ICP备案/许可证号：粤B2-20090059 
粤公网安备44030502008569号
腾讯云计算（北京）有限责任公司 京ICP证150476号 | 京ICP备11018762号