由於商品資訊及多樣性日漸龐大，而推薦系統旨在幫助緩解龐大資訊，因此推薦演算法近年來受到廣泛關注，常見的推薦演算法可分為：協同過濾推薦(Collaborative Filtering)、基於內容推薦(Content Based Filtering)、基於社群關係推薦(Social Based Filtering)、混和模型推薦(Hybrid Approach)。
近年來基於生成對抗網路(Generative Adversarial Networks)的協同過濾方法被證明能夠學習出更準確的使用者、商品隱含特徵，因此已有多項研究基於此方法延伸。然而，現行基於生成對抗網路的方法具有侷限性，首先，當訓練生成器時，由於生成器獲得的指導總是負面，而不包含正面資訊，造成生成器的訓練緩慢而不穩定。此外，現行方法並未考慮社群網路，但社群網路提供了具有相同喜好使用者的不同意見，由於不同意見可能不同地影響使用者，因此在模型訓練時，同時考慮鄰居建議至關重要。
因此在本研究中，提出改善訓練生成器的方法，使判別器回饋的訊息當中，不僅包含負面訊息，也包含正面訊息，將使生成器穩定快速的收斂，同時迭代地訓練生成對抗網路以及社群網路，使模型充分考慮具有相同喜好的鄰居，因而輸出更可靠的推薦項目。
於實驗結果中，本研究使用Amazon review data公開資料集進行訓練，根據結果顯示，本研究模型輸出準確率相較於其他基於生成對抗網路之模型能夠提升約15%的準確率。

Recommendation systems have received extensive attention recently since product information and diversity increased. Also, collaborative filtering based on Generative Adversarial Networks has been proved that can learn more accurate features of users and items. However, the current methods have limitations. First, the generator always receives negative rewards during the training process. Second, the methods do not consider other additional information.
We propose a recommender model that can improve the generator by giving negative rewards and positive rewards, so the model will converge more stably and quickly. In addition, we also add in a social network, which results in that the model can fully consider users with the same preferences, thus outputs more reliable recommendations.

Ahn, H. J. (2008). A new similarity measure for collaborative filtering to alleviate the new user cold-starting problem. Information Sciences, 178(1):37–51.

Bahdanau, D., Cho, K., and Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473.

Chae, D.-K., Kang, J.-S., Kim, S.-W., and Lee, J.-T. (2018). Cfgan: A generic collaborative filtering framework based on generative adversarial networks. In Proceedings of the 27th ACM international conference on information and knowledge management, pages 137–146.

Chen, W., Zheng, H.-T., Wang, Y., Wang, W., and Zhang, R. (2019). Utilizing generative adversarial networks for recommendation based on ratings and reviews. In 2019 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE.

Deshpande, M. and Karypis, G. (2004). Item-based top-n recommendation algorithms. ACM Transactions on Information Systems (TOIS), 22(1):143–177.

Ding, R., Guo, G., Yan, X., Chen, B., Liu, Z., and He, X. (2020). Bigan: Collaborative filtering with bidirectional generative adversarial networks. In Proceedings of the 2020 SIAM International Conference on Data Mining, pages 82–90. SIAM.

Elman, J. L. (1990). Finding structure in time. Cognitive science, 14(2):179–211.

Eslamibidgoli, M. J., Mokhtari, M., and Eikerling, M. H. (2019). Recurrent neural network-based model for accelerated trajectory analysis in aimd simulations. arXiv preprint arXiv:1909.10124.

Fan, W., Ma, Y., Yin, D., Wang, J., Tang, J., and Li, Q. (2019). Deep social collaborative filtering. In Proceedings of the 13th ACM Conference on Recommender Systems, pages 305–313.

Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial nets. In Advances in neural information processing systems, pages 2672–2680.

Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., and Courville, A. C. (2017). Improved training of wasserstein gans. In Advances in neural information processing systems, pages 5767–5777.

Hitawala, S. (2018). Comparative study on generative adversarial networks. arXiv preprint arXiv:1801.04271.

Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8):1735–1780.

Jamali, M. and Ester, M. (2010). A matrix factorization technique with trust propagation for recommendation in social networks. In Proceedings of the fourth ACM conference on Recommender systems, pages 135–142.

Kingma, D. P. and Welling, M. (2013). Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114.

Koren, Y., Bell, R., and Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer, 42(8):30–37.

Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2017). Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6):84–90.

Lee, S., Kwak, M., Tsui, K.-L., and Kim, S. B. (2019). Process monitoring using variational autoencoder for high-dimensional nonlinear processes. Engineering Applications of Artificial Intelligence, 83:13–27.

Liu, J., Pan, W., and Ming, Z. (2020). Cofigan: Collaborative filtering by generative and discriminative training for one-class recommendation. Knowledge-Based Systems, 191:105255.

Lovasz, L. et al. (1993). Random walks on graphs: A survey.´ Combinatorics, Paul erdos is eighty, 2(1):1–46.

Middleton, S. E., Shadbolt, N. R., and De Roure, D. C. (2004). Ontological user profiling in recommender systems. ACM Transactions on Information Systems (TOIS), 22(1):54–88.

Perozzi, B., Al-Rfou, R., and Skiena, S. (2014). Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 701–710.

Sarwar, B., Karypis, G., Konstan, J., and Riedl, J. (2001). Item-based collaborative filtering recommendation algorithms. In Proceedings of the 10th international conference on World Wide Web, pages 285–295.

Sun, Z. and Luo, N. (2010). A new user-based collaborative filtering algorithm combining data-distribution. In 2010 International Conference of Information Science and Management Engineering, volume 2, pages 19–23. IEEE.

Wang, J., Yu, L., Zhang, W., Gong, Y., Xu, Y., Wang, B., Zhang, P., and Zhang, D. (2017). Irgan: A minimax game for unifying generative and discriminative information retrieval models. In Proceedings of the 40th International ACM SIGIR conference on Research and Development in Information Retrieval, pages 515–524.

Yuan, F., Guo, G., Jose, J. M., Chen, L., Yu, H., and Zhang, W. (2016). Lambdafm: learning optimal ranking with factorization machines using lambda surrogates. In Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, pages 227–236.