# 資料探勘與社群網路分析

## 報告資料

* [共用資料夾](https://drive.google.com/drive/folders/1ck0CUYuQkWrthAqMVJrp8ALzVyIR8Zs7)

## 背景
* 定義推薦系統
* 何謂bundle recommendation
* 與一般推薦系統差異或難點

## 文獻回顧

1. [CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation](https://arxiv.org/abs/2206.00242 )

2. [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation]( https://arxiv.org/abs/2002.02126)

## 研究方法(可能路線)
1. 修改LightGCN架構(加入自注意力機制)
2. 研究如何獲得更有利的feature進行模型的訓練
3. 與傳統方法比較
4. 修改Representation learning的架構(需要有更明確的資料集才能利用爬蟲找到更有解釋性的關係網路資料)

## 目標

## 組員
@shinhao66
- [【论文阅读】Bundle Recommendation and Generation with Graph Neural Networks](https://blog.csdn.net/qq_43955154/article/details/125906653)
- [论文《CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation》阅读](https://blog.csdn.net/wzj1212123/article/details/131936881)
- [【论文笔记】LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation --- SIGIR2020](https://blog.csdn.net/weixin_44884854/article/details/108993222)
- [【论文笔记】：Neural Graph Collaborative](https://blog.csdn.net/qq_44015059/article/details/107461897)
- [Neural Graph Collaborative Filtering](https://arxiv.org/abs/1905.08108)
- [对比学习（Contrastive Learning）综述](https://zhuanlan.zhihu.com/p/346686467)
- YT解說 | [对比学习论文综述【论文精读】](https://www.youtube.com/watch?v=1pvxufGRuW4&t=107s)
- YT解說 | [MoCo 论文逐段精读【论文精读】](https://www.youtube.com/watch?v=pXvMXfPJZ2M)
- [【ICML 2020】SimCLR](https://zhuanlan.zhihu.com/p/197802321)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://arxiv.org/abs/2002.05709)

@wenson0106
成功訓練 CrossCBR，但具體運作原理和還在看，稍後更新