{ "id": 365716, "title": "TOP Resources | Multi-Objective Recommender System", "url": "/competitions/otto-recommender-system/discussion/365716", "author_name": "", "post_date": "2022-11-12T16:45:26.359688200Z", "votes": 15, "comment_count": 1, "views": 0, "content": "

Survey paper

\n

A survey of recommender systems with multi-objective optimization

\n
\n

Research papers with code

\n

1. Multi-Gradient Descent for Multi-Objective Recommender Systems

\n

2. Multi-Objective Neural Architecture Search Based on Diverse Structures and Adaptive Recommendation

\n
\n

Tutorial Paper

\n

Multi-Objective Recommendations: A Tutorial

\n
\n

Youtube

\n

1. Recommender System - AI-First : URL

\n

2. Recommender System - Andrew Ngt : URL

\n

3. Recommender System with Tensorflow : URL

\n

4. Recommender System - Krish Naik URL

", "messages": [ { "id": "2027199", "postDate": "11/12/2022 16:45:26", "content": "

Survey paper

\n

A survey of recommender systems with multi-objective optimization

\n
\n

Research papers with code

\n

1. Multi-Gradient Descent for Multi-Objective Recommender Systems

\n

2. Multi-Objective Neural Architecture Search Based on Diverse Structures and Adaptive Recommendation

\n
\n

Tutorial Paper

\n

Multi-Objective Recommendations: A Tutorial

\n
\n

Youtube

\n

1. Recommender System - AI-First : URL

\n

2. Recommender System - Andrew Ngt : URL

\n

3. Recommender System with Tensorflow : URL

\n

4. Recommender System - Krish Naik URL

", "rawMarkdown": "## Survey paper \n\n### [A survey of recommender systems with multi-objective optimization](https://www.sciencedirect.com/science/article/abs/pii/S0925231221017185)\n\n---\n## Research papers with code\n\n### 1. [Multi-Gradient Descent for Multi-Objective Recommender Systems](https://paperswithcode.com/paper/multi-gradient-descent-for-multi-objective)\n\n### 2. [Multi-Objective Neural Architecture Search Based on Diverse Structures and Adaptive Recommendation](https://paperswithcode.com/paper/multi-objective-neural-architecture-search-3)\n\n---\n\n## Tutorial Paper\n\n### [Multi-Objective Recommendations: A Tutorial](https://paperswithcode.com/paper/multi-objective-recommendations-a-tutorial)\n\n---\n## Youtube\n\n#### 1. Recommender System - AI-First : [URL](https://www.youtube.com/watch?v=08D_KKk3wSE&list=PLfLbmk3k5g7UyCxWcYISrwrVFHOAOpcXJ)\n#### 2. Recommender System - Andrew Ngt : [URL](https://www.youtube.com/watch?v=giIXNoiqO_U&list=PL3ZVX5cUMdLbiFgitZszhnMUZHDDEL0rS)\n#### 3. Recommender System with Tensorflow : [URL](https://www.youtube.com/watch?v=BthUPVwA59s&list=PLQY2H8rRoyvy2MiyUBz5RWZr5MPFkV3qz)\n#### 4. Recommender System - Krish Naik [URL](https://www.youtube.com/watch?v=_hf_y-_sj5Y&list=PLZoTAELRMXVN7QGpcuN-Vg35Hgjp3htvi)", "votes": null }, { "id": "2031177", "postDate": "11/15/2022 23:13:03", "content": "

Paper Title: A Multi-objective Optimization Framework for Multi-stakeholder Fairness-aware Recommendation
\nPublication date: 9 Aug 2022
\nPaper link: https://arxiv.org/pdf/2105.02951.pdf
\nPublication Author affilations: McGill University, City University of Hong Kong, Microsoft Research, Google
\nSummary: Using the Pareto Efficient hybridization to learn the weights for each of the objective Loss function we want out model to be trained on. For this we can have objectives of each kind (fairness, utility, novelty) but those objectives must be differentiable. Because we try to learn weights by solving following using multi gradient decent (MGD)
\n\"\"

", "rawMarkdown": "**Paper Title:** A Multi-objective Optimization Framework for Multi-stakeholder Fairness-aware Recommendation\n**Publication date:** 9 Aug 2022\n**Paper link:** https://arxiv.org/pdf/2105.02951.pdf\n**Publication Author affilations:** McGill University, City University of Hong Kong, Microsoft Research, Google\n**Summary:** Using the Pareto Efficient hybridization to learn the weights for each of the objective Loss function we want out model to be trained on. For this we can have objectives of each kind (fairness, utility, novelty) but those objectives must be differentiable. Because we try to learn weights by solving following using multi gradient decent (MGD)\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F3435791%2F4c094a3a5b7fc557395f8b6e8f78e652%2FScreen%20Shot%202022-10-06%20at%202.28.09%20PM.png?generation=1668553778276706&alt=media)", "votes": null } ], "comments": [ { "id": 2031177, "author_name": "muktan", "author_url": "", "post_date": "11/15/2022 23:13:03", "content": "

Paper Title: A Multi-objective Optimization Framework for Multi-stakeholder Fairness-aware Recommendation
\nPublication date: 9 Aug 2022
\nPaper link: https://arxiv.org/pdf/2105.02951.pdf
\nPublication Author affilations: McGill University, City University of Hong Kong, Microsoft Research, Google
\nSummary: Using the Pareto Efficient hybridization to learn the weights for each of the objective Loss function we want out model to be trained on. For this we can have objectives of each kind (fairness, utility, novelty) but those objectives must be differentiable. Because we try to learn weights by solving following using multi gradient decent (MGD)
\n\"\"

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "2027199": "## Survey paper \n\n### [A survey of recommender systems with multi-objective optimization](https://www.sciencedirect.com/science/article/abs/pii/S0925231221017185)\n\n---\n## Research papers with code\n\n### 1. [Multi-Gradient Descent for Multi-Objective Recommender Systems](https://paperswithcode.com/paper/multi-gradient-descent-for-multi-objective)\n\n### 2. [Multi-Objective Neural Architecture Search Based on Diverse Structures and Adaptive Recommendation](https://paperswithcode.com/paper/multi-objective-neural-architecture-search-3)\n\n---\n\n## Tutorial Paper\n\n### [Multi-Objective Recommendations: A Tutorial](https://paperswithcode.com/paper/multi-objective-recommendations-a-tutorial)\n\n---\n## Youtube\n\n#### 1. Recommender System - AI-First : [URL](https://www.youtube.com/watch?v=08D_KKk3wSE&list=PLfLbmk3k5g7UyCxWcYISrwrVFHOAOpcXJ)\n#### 2. Recommender System - Andrew Ngt : [URL](https://www.youtube.com/watch?v=giIXNoiqO_U&list=PL3ZVX5cUMdLbiFgitZszhnMUZHDDEL0rS)\n#### 3. Recommender System with Tensorflow : [URL](https://www.youtube.com/watch?v=BthUPVwA59s&list=PLQY2H8rRoyvy2MiyUBz5RWZr5MPFkV3qz)\n#### 4. Recommender System - Krish Naik [URL](https://www.youtube.com/watch?v=_hf_y-_sj5Y&list=PLZoTAELRMXVN7QGpcuN-Vg35Hgjp3htvi)", "2031177": "**Paper Title:** A Multi-objective Optimization Framework for Multi-stakeholder Fairness-aware Recommendation\n**Publication date:** 9 Aug 2022\n**Paper link:** https://arxiv.org/pdf/2105.02951.pdf\n**Publication Author affilations:** McGill University, City University of Hong Kong, Microsoft Research, Google\n**Summary:** Using the Pareto Efficient hybridization to learn the weights for each of the objective Loss function we want out model to be trained on. For this we can have objectives of each kind (fairness, utility, novelty) but those objectives must be differentiable. Because we try to learn weights by solving following using multi gradient decent (MGD)\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F3435791%2F4c094a3a5b7fc557395f8b6e8f78e652%2FScreen%20Shot%202022-10-06%20at%202.28.09%20PM.png?generation=1668553778276706&alt=media)" }, "source": "meta" }