论文周报 | 推荐系统领域最新研究进展
本次论文集合的方向主要包括基于图扩散的专家推荐算法[1]、多视图API推荐算法[2]、多行为推荐算法[3]、自适应成对训练推荐算法[4]、文化内容推荐中的共性测度[5]、一种深度学习基因推荐引擎[6]、时尚推荐[7]、长短期偏好建模的序列推荐[8]、睡眠行为推荐[9]、新闻推荐[10,11]、几何交互增强图协同过滤[12]、基于Bert的POI推荐[13]、自监督超图推荐算法[14]等。
以下整理了论文标题以及摘要，如感兴趣可移步原文精读。
1. Simplifying Sparse Expert Recommendation by Revisiting Graph Diffusion
2. API Usage Recommendation via Multi-View Heterogeneous Graph Representation Learning 3. Coarse-to-Fine Knowledge-Enhanced Multi-Interest Learning Framework for Multi-Behavior Recommendation 4. Adapting Triplet Importance of Implicit Feedback for Personalized Recommendation 5. Measuring Commonality in Recommendation of Cultural Content: Recommender Systems to Enhance Cultural Citizenship, Recsys2022 6. DeepProphet2-A Deep Learning Gene Recommendation Engine 7. Fashion Recommendation Based on Style and Social Events 8. Long Short-Term Preference Modeling for Continuous-Time Sequential Recommendation 9. Personalised recommendations of sleep behaviour with neural networks using sleep diaries captured in Sleepio 10. Understanding the Relation of User and News Representations in Content-Based Neural News Recommendation 11. Improving Few-shot News Recommendation via Cross-lingual Transfer 12. Geometric Interaction Augmented Graph Collaborative Filtering 13. BERT4Loc: BERT for Location -- POI Recommender System 14. Self-Supervised Hypergraph Transformer for Recommender Systems, KDD2022
1. Simplifying Sparse Expert Recommendation by Revisiting Graph Diffusion
Vaibhav Krishna, Nino Antulov-Fantulin
https://arxiv.org/abs/2208.02438
Community Question Answering (CQA) websites have become valuable knowledge repositories where individuals exchange information by asking and answering questions. With an ever-increasing number of questions and high migration of users in and out of communities, a key challenge is to design effective strategies for recommending experts for new questions. In this paper, we propose a simple graph-diffusion expert recommendation model for CQA, that can outperform state-of-the art deep learning representatives and collaborative models. Our proposed method learns users' expertise in the context of both semantic and temporal information to capture their changing interest and activity levels with time. Experiments on five real-world datasets from the Stack Exchange network demonstrate that our approach outperforms competitive baseline methods. Further, experiments on cold-start users (users with a limited historical record) show our model achieves an average of ~ 30% performance gain compared to the best baseline method.
2. API Usage Recommendation via Multi-View Heterogeneous Graph Representation Learning
Yujia Chen, Xiaoxue Ren, Cuiyun Gao, Yun Peng, Xin Xia, Michael R. Lyu
https://arxiv.org/abs/2208.01971
Developers often need to decide which APIs to use for the functions being implemented. With the ever-growing number of APIs and libraries, it becomes increasingly difficult for developers to find appropriate APIs, indicating the necessity of automatic API usage recommendation. Previous studies adopt statistical models or collaborative filtering methods to mine the implicit API usage patterns for recommendation. However, they rely on the occurrence frequencies of APIs for mining usage patterns, thus prone to fail for the low-frequency APIs. Besides, prior studies generally regard the API call interaction graph as homogeneous graph, ignoring the rich information (e.g., edge types) in the structure graph. In this work, we propose a novel method named MEGA for improving the recommendation accuracy especially for the low-frequency APIs. Specifically, besides call interaction graph, MEGA considers another two new heterogeneous graphs: global API co-occurrence graph enriched with the API frequency information and hierarchical structure graph enriched with the project component information. With the three multi-view heterogeneous graphs, MEGA can capture the API usage patterns more accurately. Experiments on three Java benchmark datasets demonstrate that MEGA significantly outperforms the baseline models by at least 19% with respect to the Success Rate@1 metric. Especially, for the low-frequency APIs, MEGA also increases the baselines by at least 55% regarding the Success Rate@1.
3. Coarse-to-Fine Knowledge-Enhanced Multi-Interest Learning Framework for Multi-Behavior Recommendation
Chang Meng, Ziqi Zhao, Wei Guo, Yingxue Zhang, Haolun Wu, Chen Gao, Dong Li, Xiu Li, Ruiming Tang
https://arxiv.org/abs/2208.01849
Multi-types of behaviors (e.g., clicking, adding to cart, purchasing, etc.) widely exist in most real-world recommendation scenarios, which are beneficial to learn users' multi-faceted preferences. As dependencies are explicitly exhibited by the multiple types of behaviors, effectively modeling complex behavior dependencies is crucial for multi-behavior prediction. The state-of-the-art multi-behavior models learn behavior dependencies indistinguishably with all historical interactions as input. However, different behaviors may reflect different aspects of user preference, which means that some irrelevant interactions may play as noises to the target behavior to be predicted. To address the aforementioned limitations, we introduce multi-interest learning to the multi-behavior recommendation. More specifically, we propose a novel Coarse-to-fine Knowledge-enhanced Multi-interest Learning (CKML) framework to learn shared and behavior-specific interests for different behaviors. CKML introduces two advanced modules, namely Coarse-grained Interest Extracting (CIE) and Fine-grained Behavioral Correlation (FBC), which work jointly to capture fine-grained behavioral dependencies. CIE uses knowledge-aware information to extract initial representations of each interest. FBC incorporates a dynamic routing scheme to further assign each behavior among interests. Additionally, we use the self-attention mechanism to correlate different behavioral information at the interest level. Empirical results on three real-world datasets verify the effectiveness and efficiency of our model in exploiting multi-behavior data. Further experiments demonstrate the effectiveness of each module and the robustness and superiority of the shared and specific modelling paradigm for multi-behavior data.
4. Adapting Triplet Importance of Implicit Feedback for Personalized Recommendation
Haolun Wu, Chen Ma, Yingxue Zhang, Xue Liu, Ruiming Tang, Mark Coates
https://arxiv.org/abs/2208.01709
Implicit feedback is frequently used for developing personalized recommendation services due to its ubiquity and accessibility in real-world systems. In order to effectively utilize such information, most research adopts the pairwise ranking method on constructed training triplets (user, positive item, negative item) and aims to distinguish between positive items and negative items for each user. However, most of these methods treat all the training triplets equally, which ignores the subtle difference between different positive or negative items. On the other hand, even though some other works make use of the auxiliary information (e.g., dwell time) of user behaviors to capture this subtle difference, such auxiliary information is hard to obtain. To mitigate the aforementioned problems, we propose a novel training framework named Triplet Importance Learning (TIL), which adaptively learns the importance score of training triplets. We devise two strategies for the importance score generation and formulate the whole procedure as a bilevel optimization, which does not require any rule-based design. We integrate the proposed training procedure with several Matrix Factorization (MF)- and Graph Neural Network (GNN)-based recommendation models, demonstrating the compatibility of our framework. Via a comparison using three real-world datasets with many state-of-the-art methods, we show that our proposed method outperforms the best existing models by 3-21% in terms of Recall@k for the top-k recommendation.
5. Measuring Commonality in Recommendation of Cultural Content: Recommender Systems to Enhance Cultural Citizenship, Recsys2022
Andres Ferraro, Gustavo Ferreira, Fernando Diaz, Georgina Born
https://arxiv.org/abs/2208.01696
Recommender systems have become the dominant means of curating cultural content, significantly influencing the nature of individual cultural experience. While the majority of research on recommender systems optimizes for personalized user experience, this paradigm does not capture the ways that recommender systems impact cultural experience in the aggregate, across populations of users. Although existing novelty, diversity, and fairness studies probe how systems relate to the broader social role of cultural content, they do not adequately center culture as a core concept and challenge. In this work, we introduce commonality as a new measure that reflects the degree to which recommendations familiarize a given user population with specified categories of cultural content. Our proposed commonality metric responds to a set of arguments developed through an interdisciplinary dialogue between researchers in computer science and the social sciences and humanities. With reference to principles underpinning non-profit, public service media systems in democratic societies, we identify universality of address and content diversity in the service of strengthening cultural citizenship as particularly relevant goals for recommender systems delivering cultural content. Taking diversity in movie recommendation as a case study in enhancing pluralistic cultural experience, we empirically compare systems' performance using commonality and existing utility, diversity, and fairness metrics. Our results demonstrate that commonality captures a property of system behavior complementary to existing metrics and suggest the need for alternative, non-personalized interventions in recommender systems oriented to strengthening cultural citizenship across populations of users. In this way, commonality contributes to a growing body of scholarship developing 'public good' rationales for digital media and ML systems.
6. DeepProphet2-A Deep Learning Gene Recommendation Engine
Daniele Brambilla (1), Davide Maria Giacomini (1), Luca Muscarnera, Andrea Mazzoleni (1) ((1) TheProphetAI)
https://arxiv.org/abs/2208.01918
New powerful tools for tackling life science problems have been created by recent advances in machine learning. The purpose of the paper is to discuss the potential advantages of gene recommendation performed by artificial intelligence (AI). Indeed, gene recommendation engines try to solve this problem: if the user is interested in a set of genes, which other genes are likely to be related to the starting set and should be investigated? This task was solved with a custom deep learning recommendation engine, DeepProphet2 (DP2), which is freely available to researchers worldwide via http://www.generecommender.com. Hereafter, insights behind the algorithm and its practical applications are illustrated.
The gene recommendation problem can be addressed by mapping the genes to a metric space where a distance can be defined to represent the real semantic distance between them. To achieve this objective a transformer-based model has been trained on a well-curated freely available paper corpus, PubMed. The paper describes multiple optimization procedures that were employed to obtain the best bias-variance trade-off, focusing on embedding size and network depth. In this context, the model's ability to discover sets of genes implicated in diseases and pathways was assessed through cross-validation. A simple assumption guided the procedure: the network had no direct knowledge of pathways and diseases but learned genes' similarities and the interactions among them. Moreover, to further investigate the space where the neural network represents genes, the dimensionality of the embedding was reduced, and the results were projected onto a human-comprehensible space. In conclusion, a set of use cases illustrates the algorithm's potential applications in a real word setting.
7. Fashion Recommendation Based on Style and Social Events
Federico Becattini, Lavinia De Divitiis, Claudio Baecchi, Alberto Del Bimbo
https://arxiv.org/abs/2208.00725
Fashion recommendation is often declined as the task of finding complementary items given a query garment or retrieving outfits that are suitable for a given user. In this work we address the problem by adding an additional semantic layer based on the style of the proposed dressing. We model style according to two important aspects: the mood and the emotion concealed behind color combination patterns and the appropriateness of the retrieved garments for a given type of social event. To address the former we rely on Shigenobu Kobayashi's color image scale, which associated emotional patterns and moods to color triples. The latter instead is analyzed by extracting garments from images of social events. Overall, we integrate in a state of the art garment recommendation framework a style classifier and an event classifier in order to condition recommendation on a given query.
8. Long Short-Term Preference Modeling for Continuous-Time Sequential Recommendation
Huixuan Chi, Hao Xu, Hao Fu, Mengya Liu, Mengdi Zhang, Yuji Yang, Qinfen Hao, Wei Wu
https://arxiv.org/abs/2208.00593
Modeling the evolution of user preference is essential in recommender systems. Recently, dynamic graph-based methods have been studied and achieved SOTA for recommendation, majority of which focus on user's stable long-term preference. However, in real-world scenario, user's short-term preference evolves over time dynamically. Although there exists sequential methods that attempt to capture it, how to model the evolution of short-term preference with dynamic graph-based methods has not been well-addressed yet. In particular: 1) existing methods do not explicitly encode and capture the evolution of short-term preference as sequential methods do; 2) simply using last few interactions is not enough for modeling the changing trend. In this paper, we propose Long Short-Term Preference Modeling for Continuous-Time Sequential Recommendation (LSTSR) to capture the evolution of short-term preference under dynamic graph. Specifically, we explicitly encode short-term preference and optimize it via memory mechanism, which has three key operations: Message, Aggregate and Update. Our memory mechanism can not only store one-hop information, but also trigger with new interactions online. Extensive experiments conducted on five public datasets show that LSTSR consistently outperforms many state-of-the-art recommendation methods across various lines.
9. Personalised recommendations of sleep behaviour with neural networks using sleep diaries captured in Sleepio
Alejo Nevado-Holgado, Colin Espie, Maria Liakata, Alasdair Henry, Jenny Gu, Niall Taylor, Kate Saunders, Tom Walker, Chris Miller
https://arxiv.org/abs/2208.00033
SleepioTM is a digital mobile phone and web platform that uses techniques from cognitive behavioural therapy (CBT) to improve sleep in people with sleep difficulty. As part of this process, Sleepio captures data about the sleep behaviour of the users that have consented to such data being processed. For neural networks, the scale of the data is an opportunity to train meaningful models translatable to actual clinical practice. In collaboration with Big Health, the therapeutics company that created and utilizes Sleepio, we have analysed data from a random sample of 401,174 sleep diaries and built a neural network to model sleep behaviour and sleep quality of each individual in a personalised manner. We demonstrate that this neural network is more accurate than standard statistical methods in predicting the sleep quality of an individual based on his/her behaviour from the last 10 days. We compare model performance in a wide range of hyperparameter settings representing various scenarios. We further show that the neural network can be used to produce personalised recommendations of what sleep habits users should follow to maximise sleep quality, and show that these recommendations are substantially better than the ones generated by standard methods. We finally show that the neural network can explain the recommendation given to each participant and calculate confidence intervals for each prediction, all of which are essential for clinicians to be able to adopt such a tool in clinical practice.
10. Understanding the Relation of User and News Representations in Content-Based Neural News Recommendation
Lucas Möller, Sebastian Padó
https://arxiv.org/abs/2207.14704
A number of models for neural content-based news recommendation have been proposed. However, there is limited understanding of the relative importances of the three main components of such systems (news encoder, user encoder, and scoring function) and the trade-offs involved. In this paper, we assess the hypothesis that the most widely used means of matching user and candidate news representations is not expressive enough. We allow our system to model more complex relations between the two by assessing more expressive scoring functions. Across a wide range of baseline and established systems this results in consistent improvements of around 6 points in AUC. Our results also indicate a trade-off between the complexity of news encoder and scoring function: A fairly simple baseline model scores well above 68% AUC on the MIND dataset and comes within 2 points of the published state-of-the-art, while requiring a fraction of the computational costs.
11. Improving Few-shot News Recommendation via Cross-lingual Transfer
Taicheng Guo, Lu Yu, Xiangliang Zhang
https://arxiv.org/abs/2207.14370
The cold-start problem has been commonly recognized in recommendation systems and studied by following a general idea to leverage the abundant interaction records of warm users to infer the preference of cold users. However, the performance of these solutions is limited by the amount of records available from warm users to use. Thus, building a recommendation system based on few interaction records from a few users still remains a challenging problem for unpopular or early-stage recommendation platforms. This paper focuses on solving the few-shot recommendation problem for news recommendation based on two observations. First, news at different platforms (even in different languages) may share similar topics. Second, the user preference over these topics is transferable across different platforms. Therefore, we propose to solve the few-shot news recommendation problem by transferring the user-news preference from a rich source domain to a low-resource target domain. To bridge two domains in different languages without any overlapping users and news, we propose a novel unsupervised cross-lingual transfer model as the news encoder that aligns semantically similar news in two domains. A user encoder is constructed on top of the aligned news encoding and transfers the user preference from the source to the target domain. Experimental results on two real-world news recommendation datasets show the superior performance of our proposed method on addressing few-shot news recommendation, comparing to the state-of-the-art baselines.
12. Geometric Interaction Augmented Graph Collaborative Filtering
Yiding Zhang, Chaozhuo Li, Senzhang Wang, Jianxun Lian, Xing Xie
https://arxiv.org/abs/2208.01250
Graph-based collaborative filtering is capable of capturing the essential and abundant collaborative signals from the high-order interactions, and thus received increasingly research interests. Conventionally, the embeddings of users and items are defined in the Euclidean spaces, along with the propagation on the interaction graphs. Meanwhile, recent works point out that the high-order interactions naturally form up the tree-likeness structures, which the hyperbolic models thrive on. However, the interaction graphs inherently exhibit the hybrid and nested geometric characteristics, while the existing single geometry-based models are inadequate to fully capture such sophisticated topological patterns. In this paper, we propose to model the user-item interactions in a hybrid geometric space, in which the merits of Euclidean and hyperbolic spaces are simultaneously enjoyed to learn expressive representations. Experimental results on public datasets validate the effectiveness of our proposal.
13. BERT4Loc: BERT for Location -- POI Recommender System
Syed Raza Bashir, Vojislav Misic
https://arxiv.org/abs/2208.01375
Recommending points of interest is a difficult problem that requires precise location information to be extracted from a location-based social media platform. Another challenging and critical problem for such a location-aware recommendation system is modelling users' preferences based on their historical behaviors. We propose a location-aware recommender system based on Bidirectional Encoder Representations from Transformers for the purpose of providing users with location-based recommendations. The proposed model incorporates location data and user preferences. When compared to predicting the next item of interest (location) at each position in a sequence, our model can provide the user with more relevant results. Extensive experiments on a benchmark dataset demonstrate that our model consistently outperforms a variety of state-of-the-art sequential models.
14. Self-Supervised Hypergraph Transformer for Recommender Systems, KDD2022
Lianghao Xia, Chao Huang, Chuxu Zhang
https://arxiv.org/abs/2207.14338
Graph Neural Networks (GNNs) have been shown as promising solutions for collaborative filtering (CF) with the modeling of user-item interaction graphs. The key idea of existing GNN-based recommender systems is to recursively perform the message passing along the user-item interaction edge for refining the encoded embeddings. Despite their effectiveness, however, most of the current recommendation models rely on sufficient and high-quality training data, such that the learned representations can well capture accurate user preference. User behavior data in many practical recommendation scenarios is often noisy and exhibits skewed distribution, which may result in suboptimal representation performance in GNN-based models. In this paper, we propose SHT, a novel Self-Supervised Hypergraph Transformer framework (SHT) which augments user representations by exploring the global collaborative relationships in an explicit way. Specifically, we first empower the graph neural CF paradigm to maintain global collaborative effects among users and items with a hypergraph transformer network. With the distilled global context, a cross-view generative self-supervised learning component is proposed for data augmentation over the user-item interaction graph, so as to enhance the robustness of recommender systems. Extensive experiments demonstrate that SHT can significantly improve the performance over various state-of-the-art baselines. Further ablation studies show the superior representation ability of our SHT recommendation framework in alleviating the data sparsity and noise issues. The source code and evaluation datasets are available at: https://github.com/akaxlh/SHT.