探討推薦系統之高階關係影響

Exploring High-Order Relations for Recommender Systems

陳志明(Chen Chih-Ming)

指導教授 ： 蔡銘峰 ； 楊奕軒

國立政治大學/資訊學院/社群網路與人智計算國際研究生博士學位學程(TIGP)/博士(2022年)

https://doi.org/10.6814/NCCU202201340

摘要

推薦系統已經被廣泛的運用在各種現實生活系統之中，這間接說明具實用性的推薦系統研究將會帶給世界更多的影響力，有鑑於此，我們開發了一個推薦系統架構名為SMORe，它不僅只是一個開發工具，而是被設計成具備跟上前沿研究開發可能的架構，基於此架構開發，它讓我們所提出的推薦模型皆能實現高效率且高準確度的預測，完全可與現存其他知名架構競爭，甚至表現地更好。
在此工作中，我們提出了一系列研究包含: 1) HPE, 2) Hop-Rec, 3) CSE, 4) IPR 等共四種協同過濾模型。這四種模型的共通特色為「利用高階關係改善推薦演算法」，請注意這些並非為獨立的研究，讀者可以透過我們提供的各個理論解釋來理解我們的演算法設計思維，更精簡的說明為，推薦系統相關資料集通常含有用戶與物品之間的關係，而高階關係指的是那些沒有被記錄的連結，在我們的演算法中，HPE利用隨機遊走的方式取得高階鄰居關係，用以融合用戶的異質興趣，Hop-Rec則利用隨機遊走的方式來區分用戶與物品之間的關聯強度，進而設計合適的最佳化方程式，CSE巧妙地利用蒐集到的高階鄰居關係來分群用戶與物品，從而提昇推薦的品質，IPR作為集大成，將常用的點對點協同過濾方程透過高階關係重新打造成邊對邊的協同 過濾方程，可用以清楚地解釋為何高階關係可以被有效利用在推薦系統演算法之中。

關鍵字

推薦系統 ； 協同過濾 ； 高階關係

並列摘要

Recommender system is everywhere in enterprise applications nowadays. This indicates that investigating applicable research has a more significant impact on the real world. In light of this, we developed a recommendation-purpose framework named SMORe. It is not only a toolkit but also a research-capable framework for doing cutting-edge research topics. Based on the framework, the implemented proposed models can achieve high-performance and high-accuracy predictions compared to most existing solutions.
For the proposed models, we focus on the topic of high-order relations with recommendation algorithms. Specifically, we present a series of four collaborative filtering models: 1) HPE, 2) Hop-Rec, 3) CSE, and 4) IPR. Their main features are to ‘utilize high-order relation modeling for the recommendation algorithms. Note that they are not independent works. By demonstrating their theoretical analysis, the readers can understand the rationale of our proposals. In brief, a recommendation dataset contains the user-to-item edges. The high-order information modeling is an attempt to make use of the unobserved edges. In short, HPE applies random walks to retrieve high-order neighbor data to better fuse the heterogeneous preferences. Hop-Rec determines the strongness of a high-order user-to-item pair and re-shapes the corresponding loss function. CSE shows a delicate way to cluster the users and items by high-order information and simultaneously keep and improve the recommendation quality. IPR brings the conventional entity-level CF modeling to the interaction-level CF modeling using the concept of high-order relations and finally provides an intuitive explanation about why high-order information can benefit the recommendations.

並列關鍵字

Recommender System ； Collaborative Filtering ； High-Order Relation

參考文獻

[1] G. Adomavicius and A. Tuzhilin. Context-aware recommender systems. ACM RecSys ’08.

[2] Q. Ai, V. Azizi, X. Chen, and Y. Zhang. Learning heterogeneous knowledge base embeddings for explainable recommendation. Algorithms, 2018.

[3] T.Badriyah, E.T.Wijayanto, I.Syarif, and P.Kristalina. A hybrid recommendation system for e-commerce based on product description and user profile. INTECH ’17.

[4] O. Barkan and N. Koenigstein. Item2vec: Neural item embedding for collaborative filtering.

[5] A.Bordes, N.Usunier, A.Garcia-Dura ́n, J.Weston, and O.Yakhnenko. Translating embeddings for modeling multi-relational data. NIPS ’13. Curran Associates, Inc.