머신러닝 & 딥러닝 공부/논문리뷰

읽어봐야할 논문 리스트(feat. NLP , Recsys)

조녁 2022. 12. 20. 23:29
반응형

 

 

안녕하세요~!

27년차 진로탐색꾼 조녁입니다!

 

마음속으로 숫자 100을 세면서 최대한 미루다가 드디어 정리를 합니다..

앤드류 응 선생님께서 논문을 읽기전에 읽을 리스트를 적어보라고 하셨고, 부캠 멘토님께서 읽어보고 싶은 논문 -> 정통 논문 -> 최신 논문 순으로 흥미 붙이며 읽어보라고 하셔서 우선 그렇게 리스트업 해보고자합니다.

 

 

 

[22.02.25 (금)]

그러나 어느새 28년차가 되면서 내가 멘토가 되어있구나 .. 맞아 .. 이때라도 리스트 만들고 읽었어야하는데 ㅠㅠ 

하지만 이제부터라도 읽으면 되니까!! (합리화) 다시 리스트 적어놓고 읽기 시작하자!!

이제는 법률 도메인이라는 내 도메인도 정해졌으니 관련 논문과 NLP 및 Recsys 번갈아 가면서 읽자!! 

 

원칙 : 일주일에 1편은 최소한 읽기 , 그 중에 한달에 한번은 리뷰 올리기!

 

[22.05.06 (금)]

위에 올렸던 다짐이 절반정도는 지켜졌지만, 회사에서 했던 리뷰는 올리지 못했다..

그리고 이젠 법률관련 논문을 읽을 일이 사라지고, 추천시스템 논문을 더 읽어야할 것 같아서 리스트업을 다시해본다.

원칙은 너무 빡센거같아서 일단 한달 한편 리뷰만 남겨본다. 논문은 NLP와 Recsys를 번갈아 읽고, 한편을 읽어도 제대로 읽자!!! 

 

원칙 : 한달에 한번은 리뷰 올리기!

 

[22.12.13 (화)]

5월의 다짐은 전혀 지켜지지 않았다.. 아쉬우면서도 앞으로 12월 23년에는 정해진 규칙대로 읽어나가봐야겠다.

다만, 일주일 한편은 일단 고이접어두고.. 한달에 한번이라도 리뷰올리는 걸 목표로 해봐야겠다.

우선 아래 앤드류 응 선생님의 말씀을 따라서 논문리스트부터 필요에맞게 다시 정리해보자. 

 

 

논문 읽기와 ML/DL 커리어 경력에 대한 조언 by 앤드류 응

이번 포스팅은 medium 사이트에 있는 포스팅을 번역한 글입니다! 우리 모두의 ML/DL 선생님이신 앤드류응 교수님께서 스탠포트 CS 230 강의에서 ML/DL 커리어와 논문 읽기에 대한 강의를 하신 것을 정

media-ai.tistory.com

 

 

1.  NLP 논문

  • Neural machine translation by jointly learning to align and translate(2014), D. Bahdanau et al.[pdf]23.01.25
  • Attention Is All You Need [PAPER] 23.02.01
  • KLUE: Korean Language Understanding Evaluation [PAPER]
  • BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding [PAPER] 23.02.08
  • RoBERTa: A Robustly Optimized BERT Pretraining Approach [PAPER]
  • ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators [PAPER]
  • Longformer: The Long-Document Transformer [PAPER] 23.02.21
  • An Improved Baseline for Sentence-level Relation Extraction [PAPER]
  • Improving Language Understanding by Generative Pre-Training [PAPER]
  • ALBERT: A Lite BERT for Self-supervised Learning of Language Representations [PAPER]
  • XLNET 
  • BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension [PAPER] 23.02.15
  • Don't Stop Pretraining: Adapt Language Models to Domains and Tasks [PAPER]
  • EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks [PAPER]
  • FEW-SHOT LEARNING WITH GRAPH NEURAL NETWORKS [PAPER]
  • Active Learning: Problem Settings and Recent Developments [PAPER]

 

  • Neural Architectures for Named Entity Recognition (2016), G. Lample et al. [pdf]
  • Exploring the limits of language modeling (2016), R. Jozefowicz et al. [pdf]
  • Teaching machines to read and comprehend (2015), K. Hermann et al. [pdf]
  • Effective approaches to attention-based neural machine translation (2015), M. Luong et al. [pdf]
  • Conditional random fields as recurrent neural networks (2015), S. Zheng and S. Jayasumana. [pdf]
  • Memory networks (2014), J. Weston et al. [pdf]
  • Neural turing machines (2014), A. Graves et al. [pdf]
  • Sequence to sequence learning with neural networks (2014), I. Sutskever et al. [pdf]
  • Learning phrase representations using RNN encoder-decoder for statistical machine translation (2014), K. Cho et al. [pdf]
  • A convolutional neural network for modeling sentences (2014), N. Kalchbrenner et al. [pdf]
  • Convolutional neural networks for sentence classification (2014), Y. Kim [pdf]
  • Glove: Global vectors for word representation (2014), J. Pennington et al. [pdf]
  • Distributed representations of sentences and documents (2014), Q. Le and T. Mikolov [pdf]
  • Distributed representations of words and phrases and their compositionality (2013), T. Mikolov et al. [pdf]
  • Efficient estimation of word representations in vector space (2013), T. Mikolov et al. [pdf]
  • Recursive deep models for semantic compositionality over a sentiment treebank(2013), R. Socher et al.[pdf]
  • Generating sequences with recurrent neural networks(2013), A. Graves.[pdf]

 

 

2. 추천시스템 논문

[Sequential Recommendation] 

  1. SASRec: Self-Attentive Sequential Recommendation [PAPER] 22.12.27 (화)
  2. BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer [PAPER]
  3. S3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization [PAPER] 2022.12.20 (화)
  4. NOVA-SR : Non-invasive Self-attention for Side Information Fusion in Sequential Recommendation [PAPER]
  5. Decoupled Side Information Fusion for Sequential Recommendation [PAPER] 2022.07.26 (화)

[Graph model]

  • LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation [PAPER]
  • Neural Graph Collaborative Filtering [PAPER]

[ALL] 

  1. Deep Neural Networks for YouTube Recommendations [PAPER] 2022.05.16 (월)
  2. Factorization Machines [PAPER]
  3. Field-aware Factorization Machines for CTR Prediction [PAPER]
  4. Wide & Deep Learning for Recommender Systems [PAPER]
  5. DeepFM: A Factorization-Machine based Neural Network for CTR Prediction [PAPER]
  6. MATRIX FACTORIZATION TECHNIQUES FOR RECOMMENDER SYSTEMS [PAPER]
  7. A Contextual-Bandit Approach to Personalized News Article Recommendation [PAPER]
  8. Neural Collaborative Filtering [PAPER]

=> 위에 논문들 다 읽고 아래것들 정리하면서 필요에 따라 읽자.

  1. Hybrid Recommender Systems: Survey and Experiments
  2. Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions
  3. A Survey of Explanations in Recommender Systems
  4. A Survey of Collaborative Filtering Techniques
  5. A Survey of Accuracy Evaluation Metrics of Recommendation Tasks
  6. Tag-Aware Recommender Systems: A State-of-the-art Survey
  7. Recommender Systems Survey
  8. Social Recommendation: A Review
  9. Collaborative Filtering beyond the User-Item Matrix: A Survey of the State of the Art and Future Challenges
  10. Time-aware Recommender Systems: A Comprehensive Survey and Analysis of Existing Evaluation Protocols
  11. Shilling Attacks against Recommender Systems: A Comprehensive Survey
  12. Recommender Systems Based on User Reviews: The State of the Art
  13. Parallel and Distributed Collaborative Filtering: A Survey
  14. Interactive Recommender Systems: A Survey of the State of the Art and Future Research Challenges and Opportunities
  15. A Survey of Active Learning in Collaborative Filtering Recommender Systems
  16. A Survey of Serendipity in Recommender Systems
  17. Cross Domain Recommender Systems: A Systematic Literature Review
  18. Diversity in Recommender Systems – A Survey
  19. Diversity, Serendipity, Novelty, and Coverage: A Survey and Empirical Analysis of Beyond-Accuracy Objectives in Recommender Systems
  20. Explainable Recommendation: A Survey and New Perspectives
  21. Sequence-Aware Recommender Systems
  22. Research Commentary on Recommendations with Side Information: A Survey and Research Directions
  23. Deep Learning based Recommender System: A Survey and New Perspectives
  24. A Review on Deep Learning for Recommender Systems: Challenges and Remedies
  25. Sequential Recommender Systems: Challenges, Progress and Prospects [PAPER]
  26. A Survey on Group Recommender Systems
  27. A Survey on Knowledge Graph-Based Recommender Systems
  28. Bias and Debias in Recommender System: A Survey and Future Directions
  29. Graph Neural Networks in Recommender Systems: A Survey
  30. A Survey on Session-based Recommender Systems 2021
  31. A Survey on Conversational Recommender Systems 2021
  32. A Survey on Neural Recommendation: From Collaborative Filtering to Content and Context Enriched Recommendation 2021
 

 

3. 최신 논문

  • Zero-Shot Text-to-Image Generation [PAPER]
  • LaMDA: Language Models for Dialog Applications [PAPER]
  • PaLM: Scaling Language Modeling with Pathways [PAPER]

 

반응형
저작자표시