ACM?SIGKDD（國(guó)際數(shù)據(jù)挖掘與知識(shí)發(fā)現(xiàn)大會(huì)，簡(jiǎn)稱KDD）會(huì)議始于1989年，是數(shù)據(jù)挖掘領(lǐng)域歷史最悠久、規(guī)模最大的國(guó)際頂級(jí)學(xué)術(shù)會(huì)議，也是首個(gè)引入大數(shù)據(jù)、數(shù)據(jù)科學(xué)、預(yù)測(cè)分析、眾包等概念的會(huì)議，每年吸引了大量數(shù)據(jù)挖掘、機(jī)器學(xué)習(xí)、大數(shù)據(jù)和人工智能等領(lǐng)域的研究學(xué)者、從業(yè)人員參與。

AMiner通過(guò)AI技術(shù)，對(duì) KDD2023 收錄的會(huì)議論文進(jìn)行了分類整理，今日分享的是Recommendation主題論文！（由于篇幅關(guān)系，本篇只展現(xiàn)部分論文，點(diǎn)擊閱讀原文可直達(dá)KDD頂會(huì)頁(yè)面查看所有論文）

1.Adaptive Graph Contrastive Learning for Recommendation

鏈接：https://www.aminer.cn/pub/6466fafbd68f896efaeb7633/

2.Tree based Progressive Regression Model for Watch-Time Prediction in Short-video Recommendation

鏈接：https://www.aminer.cn/pub/648000a9d68f896efaa123eb/

3.Multi-channel Integrated Recommendation with Exposure Constraints

鏈接：https://www.aminer.cn/pub/646c3ad0d68f896efa5ce60f/

4.ReLoop2: Building Self-Adaptive Recommendation Models via Responsive Error Compensation Loop

鏈接：https://www.aminer.cn/pub/648bde68d68f896efaf81bd3/

5.Hierarchical Invariant Learning for Domain Generalization Recommendation

鏈接：https://www.aminer.cn/pub/64af9a073fda6d7f065a6d92/

6.Debiasing Recommendation by Learning Identifiable Latent Confounders

鏈接：https://www.aminer.cn/pub/63e9aa5e90e50fcafd133661/

7.Meta Graph Learning for Long-tail Recommendation

鏈接：https://www.aminer.cn/pub/64af9a033fda6d7f065a6963/

8.PGLBox: Multi-GPU Graph Learning Framework for Web-Scale Recommendation

鏈接：https://www.aminer.cn/pub/64af9a043fda6d7f065a6a90/

9.Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delay

鏈接：https://www.aminer.cn/pub/64af9a063fda6d7f065a6b9c/

10.Privacy Matters: Vertical Federated Linear Contextual Bandits for Privacy Protected Recommendation

鏈接：https://www.aminer.cn/pub/64af9a0a3fda6d7f065a702d/

11.Generative Flow Network for Listwise Recommendation

鏈接：https://www.aminer.cn/pub/64af99fc3fda6d7f065a6275/

12.A Sublinear Time Algorithm for Opinion Optimization in Directed Social Networks via Edge Recommendation

鏈接：https://www.aminer.cn/pub/64af99fc3fda6d7f065a62a4/

13.Hierarchical Projection Enhanced Multi-behavior Recommendation

鏈接：https://www.aminer.cn/pub/64af99fe3fda6d7f065a6424/

14.SAMD: An Industrial Framework for Heterogeneous Multi-Scenario Recommendation

鏈接：https://www.aminer.cn/pub/64af99fe3fda6d7f065a6481/

15.M5: Multi-Modal Multi-Interest Multi-Scenario Matching for Over-the-Top Recommendation

鏈接：https://www.aminer.cn/pub/64af9a033fda6d7f065a691f/

16.Modeling Dual Period-Varying Preferences for Takeaway Recommendation

鏈接：https://www.aminer.cn/pub/64af9a053fda6d7f065a6b8b/

17.Reconsidering Learning Objectives in Unbiased Recommendation: A Distribution Shift Perspective

鏈接：https://www.aminer.cn/pub/64af9a083fda6d7f065a6db2/

18.Who Should Be Given Incentives? Counterfactual Optimal Treatment Regimes Learning for Recommendation

鏈接：https://www.aminer.cn/pub/64af9a083fda6d7f065a6dd5/

如何使用ChatPaper讀文獻(xiàn)？

為了讓更多科研人更高效的獲取文獻(xiàn)知識(shí)，AMiner基于GLM-130B大模型能力，開發(fā)了Chatpaper，幫助科研人快速提高檢索、閱讀論文效率，獲取最新領(lǐng)域研究動(dòng)態(tài)，讓科研工作更加游刃有余。

ChatPaper是一款集檢索、閱讀、知識(shí)問(wèn)答于一體的對(duì)話式私有知識(shí)庫(kù)，AMiner希望通過(guò)技術(shù)的力量，讓大家更加高效地獲取知識(shí)。

ChatPaper：https://www.aminer.cn/chat/g