Recsys2021 | 推薦系統(tǒng)論文整理和導(dǎo)讀
本期主要整理和分類了Recsys 2021的Research Papers和Reproducibility papers。按照推薦系統(tǒng)的研究方向和使用的推薦技術(shù)來(lái)分類，方便大家快速檢索自己感興趣的文章。個(gè)人認(rèn)為Recsys這個(gè)會(huì)議重點(diǎn)不在于"技術(shù)味多濃"或者"技術(shù)多先進(jìn)"，而在于經(jīng)常會(huì)涌現(xiàn)很多新的觀點(diǎn)以及有意思的研究點(diǎn)，涵蓋推薦系統(tǒng)的各個(gè)方面，例如，Recsys 2021涵蓋的一些很有意思的研究點(diǎn)包括：
推薦系統(tǒng)的信息繭房和回音室問(wèn)題的探討，有4篇文章探討了社交媒體推薦、音樂(lè)推薦和視頻推薦中的信息繭房和回音室效應(yīng)。很少見(jiàn)到在學(xué)術(shù)會(huì)議上專門(mén)討論這樣深刻的問(wèn)題，值得一讀。 推薦系統(tǒng)評(píng)估體系的探討，對(duì)推薦系統(tǒng)整個(gè)評(píng)估體系的梳理，多個(gè)指標(biāo)間如何做權(quán)衡等。 推薦系統(tǒng)的交互設(shè)計(jì)探討，探討了美食推薦場(chǎng)景下用戶交互設(shè)計(jì)。關(guān)于用戶界面/交互設(shè)計(jì)的推薦系統(tǒng)文章還是很新奇的。 推薦系統(tǒng)中的探索與利用探討，例如Google關(guān)于用戶探索的工作Values of User Exploration in Recommender Systems值得一讀。 對(duì)已有工作的探討和挑戰(zhàn)，傳統(tǒng)矩陣分解推薦系統(tǒng)和深度學(xué)習(xí)推薦系統(tǒng)的對(duì)比。例如：何向南老師的NCF工作和MF的對(duì)比，繼Recsys20被進(jìn)行對(duì)比后, 在Recsys21上又再次被擺上了臺(tái)面進(jìn)行對(duì)比。 Recsys20, Rendle S, Krichene W, Zhang L, et al. Neural collaborative filtering vs. matrix factorization revisited[C]//Fourteenth ACM Conference on Recommender Systems. 2020: 240-248. Recsys21, Anelli V W, Bellogín A, Di Noia T, et al. Reenvisioning the comparison between Neural Collaborative Filtering and Matrix Factorization[C]//Fifteenth ACM Conference on Recommender Systems. 2021: 521-529.
還有些研究點(diǎn)也是值得一讀的，比如推薦系統(tǒng)中的冷啟動(dòng)，偏差與糾偏，序列推薦，可解釋性，隱私保護(hù)等，這些研究很有意思和啟發(fā)性，有助于開(kāi)拓大家的研究思路。
下面主要根據(jù)自己讀題目或者摘要時(shí)的一些判斷做的歸類，按照推薦系統(tǒng)研究方向分類、推薦技術(shù)分類以及專門(mén)實(shí)驗(yàn)性質(zhì)的可復(fù)現(xiàn)型文章分類，可能存在漏歸和錯(cuò)歸的情況，請(qǐng)大家多多指正。
1.按照推薦系統(tǒng)研究方向分類
1.1 信息繭房和回音室
信息繭房/回音室(echo chamber)/過(guò)濾氣泡(filter bubble)，這3個(gè)概念類似，在國(guó)內(nèi)外有不同的說(shuō)法。大致是指使用社交媒體以及帶有算法推薦功能的資訊類APP，可能會(huì)導(dǎo)致我們只看得到自己感興趣的、認(rèn)同的內(nèi)容，進(jìn)而讓大家都活在自己的小世界里，彼此之間難以認(rèn)同和溝通。關(guān)于這部分的概念可參見(jiàn)知乎文章：https://zhuanlan.zhihu.com/p/71844281。有四篇文章探討了這樣的問(wèn)題。
The Dual Echo Chamber: Modeling Social Media Polarization for Interventional Recommending
Tim Donkers and Jürgen Ziegler
I want to break free! Recommending friends from outside the echo chamber
Antonela Tommasel, Juan Manuel Rodriguez, and Daniela Godoy
Follow the guides: disentangling human and algorithmic curation in online music consumption
Quentin Villermet, Jérémie Poiroux, Manuel Moussallam, Thomas Louail, and Camille Roth
An Audit of Misinformation Filter Bubbles on YouTube: Bubble Bursting and Recent Behavior Changes
Matus Tomlein, Branislav Pecher, Jakub Simko, Ivan Srba, Robert Moro, Elena Stefancova, Michal Kompan, Andrea Hrckova, Juraj Podrouzek, and Maria Bielikova
1.2 探索與利用
此次大會(huì)在探索與利用上也有很多探討，例如多臂老虎機(jī)、谷歌的新工作，即：用戶側(cè)的探索等。
Burst-induced Multi-Armed Bandit for Learning Recommendation
Rodrigo Alves, Antoine Ledent, and Marius Kloft
Values of User Exploration in Recommender Systems
Google, Minmin Chen, Yuyan Wang, Can Xu, Ya Le, mohit sharma, Lee Richardson, and Ed Chi
Designing Online Advertisements via Bandit and Reinforcement Learning
Yusuke Narita, Shota Yasui, and Kohei Yata
The role of preference consistency, defaults and musical expertise in users’ exploration behavior in a genre exploration recommender
Yu Liang and Martijn C. Willemsen
Top-K Contextual Bandits with Equity of Exposure
Olivier Jeunen and Bart Goethals
1.3 偏差與糾偏
涉及排序?qū)W習(xí)的糾偏、用戶的偏差探索等。
Debiased Explainable Pairwise Ranking from Implicit Feedback
Khalil Damak, Sami Khenissi, and Olfa Nasraoui
Mitigating Confounding Bias in Recommendation via Information Bottleneck
Dugang Liu, Pengxiang Cheng, Hong Zhu, Zhenhua Dong, Xiuqiang He, Weike Pan, and Zhong Ming
User Bias in Beyond-Accuracy Measurement of Recommendation Algorithms
Ningxia Wang, and Li Chen
1.4 冷啟動(dòng)
利用圖學(xué)習(xí)、表征學(xué)習(xí)等做冷啟動(dòng)。
Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders
Guillaume Salha-Galvan, Romain Hennequin, Benjamin Chapus, Viet-Anh Tran, and Michalis Vazirgiannis
Shared Neural Item Representations for Completely Cold Start Problem
Ramin Raziperchikolaei, Guannan Liang, and Young-joo Chung
1.5 評(píng)估體系
涉及離線或在線評(píng)估方法，準(zhǔn)確性和多樣性等統(tǒng)一指標(biāo)的設(shè)計(jì)等。
Evaluating Off-Policy Evaluation: Sensitivity and Robustness
Yuta Saito, Takuma Udagawa, Haruka Kiyohara, Kazuki Mogi, Yusuke Narita, and Kei Tateno
Fast Multi-Step Critiquing for VAE-based Recommender Systems
Diego Antognini and Boi Faltings
Online Evaluation Methods for the Causal Effect of Recommendations
Masahiro Sato
Towards Unified Metrics for Accuracy and Diversity for Recommender Systems
Javier Parapar and Filip Radlinski
1.6 會(huì)話/序列推薦
涉及session維度的短序列推薦；使用NLP中常用的Transformers做序列推薦的鴻溝探討和解決，這個(gè)工作本人還挺感興趣的，后續(xù)會(huì)精讀下！
Next-item Recommendations in Short Sessions
Wenzhuo Song, Shoujin Wang, Yan Wang, and SHENGSHENG WANG
Transformers4Rec: Bridging the Gap between NLP and Sequential / Session-Based Recommendation
Gabriel de Souza Pereira Moreira, Sara Rabhi, Jeong Min Lee, Ronay Ak, and Even Oldridge
Denoising User-aware Memory Network for Recommendation
Zhi Bian, Shaojun Zhou, Hao Fu, Qihong Yang, Zhenqi Sun, Junjie Tang, Guiquan Liu, kaikui liu, and Xiaolong Li
Large-Scale Modeling of Mobile User Click Behaviors Using Deep Learning
Xin Zhou and Yang Li
1.7 隱私保護(hù)
結(jié)合聯(lián)邦學(xué)習(xí)做隱私保護(hù)等。
Privacy Preserving Collaborative Filtering by Distributed Mediation
Alon Ben Horin, and Tamir Tassa
Stronger Privacy for Federated Collaborative Filtering With Implicit Feedback
Lorenzo Minto, Moritz Haller, Ben Livshits, and Hamed Haddadi
1.8 對(duì)抗與攻擊
Black-Box Attacks on Sequential Recommenders via Data-Free Model Extraction
Zhenrui Yue, Zhankui He, Huimin Zeng, and Julian McAuley
1.9 對(duì)話推薦系統(tǒng)
Large-scale Interactive Conversational Recommendation System
Ali Montazeralghaem, James Allan, and Philip S. Thomas
1.10 可解釋性推薦
EX3: Explainable Attribute-aware Item-set Recommendations
Yikun Xian, Tong Zhao, Jin Li, Jim Chan, Andrey Kan, Jun Ma, Xin Luna Dong, Christos Faloutsos, George Karypis, S. Muthukrishnan, and Yongfeng Zhang
1.11 跨域推薦
Towards Source-Aligned Variational Models for Cross-Domain Recommendation
Aghiles Salah, Thanh Binh Tran, and Hady Lauw
1.12 基于視覺(jué)的推薦
利用視覺(jué)信息做推薦。
Semi-Supervised Visual Representation Learning for Fashion Compatibility
Ambareesh Revanur, Vijay Kumar, and Deepthi Sharma
Tops, Bottoms, and Shoes: Building Capsule Wardrobes via Cross-Attention Tensor Network
Huiyuan Chen, Yusan Lin, Fei Wang, and Hao Yang
1.13 組推薦/用戶物品分層推薦
Local Factor Models for Large-Scale Inductive Recommendation
Longqi Yang, Tobias Schnabel, Paul N. Bennett, and Susan Dumais
Learning to Represent Human Motives for Goal-directed Web Browsing
Jyun-Yu Jiang, Chia-Jung Lee, Longqi Yang, Bahareh Sarrafzadeh, Brent Hecht, Jaime Teevan
1.14 推薦系統(tǒng)交互設(shè)計(jì)
探討了美食場(chǎng)景下，多用戶意圖的推薦系統(tǒng)的交互設(shè)計(jì)。
“Serving Each User”: Supporting Different Eating Goals Through a Multi-List Recommender Interface
Alain Starke, Edis Asotic, and Christoph Trattner
2. 按照推薦技術(shù)分類
涉及傳統(tǒng)協(xié)同過(guò)濾、度量學(xué)習(xí)的迭代；新興的圖學(xué)習(xí)技術(shù)、聯(lián)邦學(xué)習(xí)技術(shù)、強(qiáng)化學(xué)習(xí)技術(shù)等的探索。
2.1 協(xié)同過(guò)濾
探索了傳統(tǒng)的協(xié)同過(guò)濾工作，其中第一篇工作把CF和LDA聯(lián)系在了一起，挺有意思。
Matrix Factorization for Collaborative Filtering Is Just Solving an Adjoint Latent Dirichlet Allocation Model After All
Florian Wilhelm
Negative Interactions for Improved Collaborative-Filtering: Don’t go Deeper, go Higher
Harald Steck and Dawen Liang
ProtoCF: Prototypical Collaborative Filtering for Few-shot Item Recommendation
Aravind Sankar, Junting Wang, Adit Krishnan, and Hari Sundaram
2.2 圖學(xué)習(xí)
知識(shí)圖譜的應(yīng)用以及圖嵌入技術(shù)和上下文感知的表征技術(shù)的融合，這兩個(gè)工作個(gè)人都挺感興趣。
Sparse Feature Factorization for Recommender Systems with Knowledge Graphs
Together is Better: Hybrid Recommendations Combining Graph Embeddings and Contextualized Word Representations
?Marco Polignano, Cataldo Musto, Marco de Gemmis, Pasquale Lops, and? ? ? ?Giovanni Semeraro
2.3 強(qiáng)化學(xué)習(xí)
強(qiáng)化學(xué)習(xí)在推薦系統(tǒng)中的應(yīng)用，和對(duì)話系統(tǒng)結(jié)合在一起；獎(jiǎng)勵(lì)函數(shù)的設(shè)計(jì)等。
Partially Observable Reinforcement Learning for Dialog-based Interactive Recommendation
Yaxiong Wu, Craig Macdonald, and Iadh Ounis,
Pessimistic Reward Models for Off-Policy Learning in Recommendation
Olivier Jeunen and Bart Goethals
2.4 度量學(xué)習(xí)
協(xié)同過(guò)濾和度量學(xué)習(xí)的結(jié)合，即：CML。
Hierarchical Latent Relation Modeling for Collaborative Metric Learning
Viet-Anh Tran, Guillaume Salha-Galvan, Romain Hennequin, and Manuel Moussallam
2.5 聯(lián)邦學(xué)習(xí)
聯(lián)邦學(xué)習(xí)的優(yōu)化以及在隱私保護(hù)中的應(yīng)用。
A Payload Optimization Method for Federated Recommender Systems
Farwa K. Khan, Adrian Flanagan, Kuan Eeik Tan, Zareen Alamgir, and Muhammad Ammad-ud-din
Stronger Privacy for Federated Collaborative Filtering With Implicit Feedback
? ? ?Lorenzo Minto, Moritz Haller, Ben Livshits, and Hamed Haddadi
2.6 架構(gòu)/訓(xùn)練/優(yōu)化
涉及訓(xùn)練、優(yōu)化、檢索、實(shí)時(shí)流等。
cDLRM: Look Ahead Caching for Scalable Training of Recommendation Models
Keshav Balasubramanian, Abdulla Alshabanah, Joshua D Choe, and Murali Annavaram
Reverse Maximum Inner Product Search: How to efficiently find users who would like to buy my item?
Daichi Amagata and Takahiro Hara
Page-level Optimization of e-Commerce Item RecommendationsChieh Lo, Hongliang Yu, Xin Yin, Krutika Shetty, Changchen He, Kathy Hu, Justin M Platz, Adam Ilardi, and Sriganesh Madhvanath
Accordion: A Trainable Simulator for Long-Term Interactive Systems
James McInerney, Ehtsham Elahi, Justin Basilico, Yves Raimond, and Tony Jebara
Information Interactions in Outcome Prediction: Quantification and Interpretation using Stochastic Block Models
Ga?l Poux-Médard, Julien Velcin, and Sabine Loudcher
Learning An Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems
Danni Peng, Sinno Jialin Pan, Jie Zhang, and Anxiang Zeng
Recommendation on Live-Streaming Platforms: Dynamic Availability and Repeat Consumption
Jeremie Rappaz, Julian McAuley, and Karl Aberer
3. 實(shí)驗(yàn)性質(zhì)的文章
Reproducibility papers可復(fù)現(xiàn)實(shí)驗(yàn)性質(zhì)的文章，共3篇。分別探索了：序列推薦中的采樣評(píng)估策略；對(duì)話推薦系統(tǒng)中生成式和檢索式的方法對(duì)比；神經(jīng)網(wǎng)絡(luò)推薦系統(tǒng)和矩陣分解推薦系統(tǒng)的對(duì)比。
A Case Study on Sampling Strategies for Evaluating Neural Sequential Item Recommendation Models
by Alexander Dallmann, Daniel Zoller, Andreas Hotho (Data Science Chair, University of Würzburg, Würzburg, Germany)
Generation-based vs. Retrieval-based Conversational Recommendation: A User-Centric Comparison
by Ahtsham Manzoor and Dietmar Jannach (University of Klagenfurt, Klagenfurt, Austria)
Reenvisioning the comparison between Neural Collaborative Filtering and Matrix Factorization
by Vito Walter Anelli (Polytechnic University of Bari, Bari, Italy), Alejandro Bellogin (Information Retrieval Group, Universidad Autonoma de Madrid, Madrid, Spain), Tommaso Di Noia Polytechnic (University of Bari, Bari, Italy), and Claudio Pomo (Polytechnic University of Bari, Bari, Italy)
總結(jié)
通過(guò)此次的論文的整理和分類，筆者也發(fā)現(xiàn)了一些自己感興趣的研究點(diǎn)，比如：推薦系統(tǒng)的回音室效應(yīng)探討文章；Transformers在序列推薦和NLP序列表征中的鴻溝和解決文章：Transformers4Rec；圖嵌入表征和上下文感知表征的融合文章；NCF和MF的實(shí)驗(yàn)對(duì)比文章；谷歌的用戶探索文章等。希望讀者也能夠發(fā)現(xiàn)自己感興趣的文章。下期分享見(jiàn)！