【推薦系統(tǒng)】AAAI2022推薦系統(tǒng)論文集錦
2022年第36屆人工智能頂級(jí)會(huì)議AAAI論文列表已經(jīng)放出，此次會(huì)議共收到9251篇論文提交，其中9020篇論文被審稿。最終錄取篇數(shù)為1349篇，錄取率為可憐的15%。由于境外疫情形勢(shì)依然嚴(yán)峻，大會(huì)將在2月22日到3月1日在線上進(jìn)行舉辦。
較之歷年接受率來說，今年的錄取率可以說是斷崖式下跌。下圖對(duì)2017年至今年的投稿量以及接受率進(jìn)行了可視化，可以說今年的投稿量之多與接受率之低形成了鮮明的對(duì)比。
深度學(xué)習(xí)技術(shù)仍然是比較火熱的技術(shù)之一；
對(duì)圖數(shù)據(jù)的研究依然是大家關(guān)注的數(shù)據(jù)形式之一；
自監(jiān)督學(xué)習(xí)、半監(jiān)督學(xué)習(xí)、多智能體、表示學(xué)習(xí)是大家主要使用的學(xué)習(xí)范式；
機(jī)器學(xué)習(xí)應(yīng)用如目標(biāo)檢測(cè)、文本分類、語義分割等是目前大家比較關(guān)注的方向。
完整版清單可從官網(wǎng)下載查看。
https://aaai.org/Conferences/AAAI-22/wp-content/uploads/2021/12/AAAI-22_Accepted_Paper_List_Main_Technical_Track.pdf
1. Meta-Learning for Online Update of Recommender Systems
Minseok Kim, Hwanjun Song, Yooju Shin, Dongmin Park, Kijung Shin, Jae-Gil Lee
2.?DiPS: Differentiable Policy for Sketching in Recommender Systems
Aritra Ghosh, Saayan Mitra, Andrew Lan
3.?Low-pass Graph Convolutional Network for Recommendation
4.?Online certification of preference-based fairness for personalized recommender systems
Virginie Do, Sam Corbett-Davies, Jamal Atif, Nicolas Usunier
5.?Modeling Attrition in Recommender Systems with Departing Bandits
6.?A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations
7.?Context Uncertainty in Contextual Bandits with Applications to Recommender Systems
8.?Multi-view Intent Disentangle Graph Networks for Bundle Recommendation
9.?SMINet: State-Aware Multi-Aspect Interests Representation Network for Cold-Start Users Recommendation
10.?Leaping Through Time with Gradient-based Adaptation for Recommendation
Nuttapong Chairatanakul, Hoang NT, Xin Liu, Tsuyoshi Murata
11.?Cross-Task Knowledge Distillation in Multi-Task Recommendation
12.?FPAdaMetric: False-positive-aware Adaptive Metric Learning for Session-based Recommendation
13.?Offline Interactive Recommendation with Natural-Language Feedback
14.?Learning the Optimal Recommendation from Explorative Users
Fan Yao, Chuanhao Li, Denis Nekipelov, Hongning Wang, Haifeng Xu
15.?Obtaining Calibrated Probabilities with Personalized Ranking Models
Wonbin Kweon, SeongKu Kang, Hwanjo Yu
通過整理發(fā)現(xiàn)，此次會(huì)議接收的推薦系統(tǒng)相關(guān)論文主要涉及基于元學(xué)習(xí)的推薦系統(tǒng)2篇，序列化推薦5篇，基于強(qiáng)化學(xué)習(xí)的推薦系統(tǒng)4篇以及冷啟動(dòng)推薦2篇。
往期精彩回顧