【学术相关】AAAI2021推荐系统论文清单
深度学习技术依然是目前来看比较火热的技术之一;
图结构数据(网络/知识图谱)依然是大家比较关注的数据形式之一;
强化学习/对抗学习/多任务学习范式是大家主要使用的手段之一;
动态性/高效性/鲁棒性/无监督学习是目前大家比较关注的话题;
相较于去年的热度分布来看,Embedding技术/Attention技术相对来说热度有所下降。更多去年AAAI2020相关的信息可以移步AAAI2020推荐系统论文集锦。
AAAI2021接收论文标题词云
接下来,特意从1692篇论文中筛选出与推荐系统相关的33篇文章供大家欣赏(去年的推荐系统论文文章的比例为27/1590),提前领略学术前沿趋势与牛人的最新想法。
推荐系统相关文章
RevMan: Revenue-Aware Multi-Task Online Insurance Recommendation 收入感知的多任务在线保险推荐(很对,卖保险还真得看收入) |
Detecting Beneficial Feature Interactions for Recommender Systems 为推荐系统检测有益的特征(有用的交叉特征对于推荐来说非常重要) |
FedRec++: Lossless Federated Recommendation with Explicit Feedback 带有显式反馈的无损联邦推荐系统(好奇联邦学习范式如何做到无损的) |
Graph Heterogeneous Multi-Relational Recommendation 图异构多关系推荐系统(多种关系的异构图数据处理并不容易) |
Hierarchical Reinforcement Learning for Integrated Recommendation 层次化的强化学习综合推荐系统 |
Who You Would Like to Share With? A Study of Share Recommendation in Social ECommerce 社交电商中分享行为的研究(好奇是什么因素影响我们分享的) |
Self-Supervised Hypergraph Convolutional Networks for Session-Based Recommendation 用于会话推荐的自监督超图卷积网络(超图能够建模更复杂的图关系) |
Dual Sparse Attention Network for Session-Based Recommendation 用于会话推荐的双稀疏注意力网络 |
U-BERT: Pre-Training User Representations for Improved Recommendation 预训练BERT模型用于用户表示来提高推荐性能 |
Fairness-Aware News Recommendation with Decomposed Adversarial Learning 分解的对抗学习用于公平性的新闻推荐 |
Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation 知识增强的层级图Transformer网络用于多行为推荐 |
Cold-Start Sequential Recommendation via Meta Learner 基于元学习器的冷启动序列化推荐 |
A User-Adaptive Layer Selection Framework for Very Deep Sequential Recommender Models 用户自适应层筛选框架用于极深度序列化推荐模型 |
A Hybrid Bandit Framework for Diversified Recommendation 一个混合的Bandit框架用于多样化推荐 |
PREMERE: Meta-Reweighting via Self-Ensembling for Point-of-Interest Recommendation 通过自集成来进行元权重重调用于POI推荐 |
DEAR: Deep Reinforcement Learning for Online Advertising Impression in Recommender Systems 深度强化学习用于推荐系统中的在线广告印象中(Impression是在线广告中的专有词,大家可以具体查查) |
Noninvasive Self-Attention for Side Information Fusion in Sequential Recommendation 无创自注意力机制用于序列推荐中的附加信息融合 |
Knowledge-Enhanced Top-K Recommendation in Poincaré Ball 知识增强的Top-K推荐(Poincaré Ball是个什么Ball,不太懂) |
Out-of-Town Recommendation with Travel Intention Modeling 带有旅游意图建模的POI推荐 |
Learning to Recommend from Sparse Data via Generative User Feedback 通过生成式用户反馈来学习从稀疏数据进行推荐 |
Hierarchical Negative Binomial Factorization for Recommender Systems on Implicit Feedback 基于隐式反馈的递阶负二项式分解用于推荐系统 |
Disposable Linear Bandits for Online Recommendations 一次性线性Bandits用于在线推荐 |
Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation 带有解纠缠的普遍价值函数的强化学习用于项目推荐 |
Dynamic Memory Based Attention Network for Sequential Recommendation 动态记忆注意力网络用于序列化推荐 |
Asynchronous Stochastic Gradient Descent for Extreme-Scale Recommender Systems 异步随机梯度下降算法在极端尺度推荐系统中的应用 |
On Estimating Recommendation Evaluation Metrics under Sampling 关于采样情况下的推荐评价指标的估计 |
Knowledge-Aware Coupled Graph Neural Network for Social Recommendation 面向社交推荐的知识感知耦合图神经网络 |
Graph-Enhanced Multi-Task Learning of Multi-Level Transition Dynamics for Session-Based Recommendation 多层次动态过渡的图增强多任务学习用于会话推荐 |
Deep Transfer Tensor Decomposition with Orthogonal Constraint for Recommender Systems 基于正交约束的深度迁移张量分解算法 |
A General Offline Reinforcement Learning Framework for Interactive Recommendation 一个用于交互式推荐的通用离线强化学习框架 |
Intelligent Recommendations for Citizen Science 公民科学的智能推荐(公民科学指的是在科学家指导下的公民参与的众包平台项目) |
Degree Planning with PLAN-BERT: Multi-Semester Recommendation Using Future Courses of Interest 使用未来感兴趣的课程进行多学期推荐 |
Personalized Adaptive Meta Learning for Cold-Start User Preference Prediction 基于个性化自适应元学习的冷启动用户偏好预测 |
最后贴上之前总结的顶会中推荐系统相关的论文供大家进行横向和纵向对比学习。
往期精彩回顾
获取本站知识星球优惠券,复制链接直接打开:
https://t.zsxq.com/qFiUFMV
本站qq群704220115。
加入微信群请扫码: