Learning User Preferences Research Articles

Denoising Alignment with Large Language Model for Recommendation

The mainstream approach of GNN-based recommendation aggregates high-order ID information associated with the node in the user-item graph. The aggregation pattern using ID as signal has two disadvantages: lack of textual semantics and the impact of interaction noise. These disadvantages pose a threat to effectively learn user preferences, especially in capturing intricate user-item semantic relationships. Although large language models (LLMs) allow the integration of rich textual information into recommenders and have had groundbreaking applications in recommender systems, current works need to bridge the gap between different representation spaces. This is because LLMs-based methods align the representations of GNN-based models only by using text embedding of LLM, leading to unsatisfactory results. To address this challenge, we propose a D enoising A lignment framework with L LMs for GNN-based R ecommenders (DALR), which aims to align structural representation with textual representation and mitigate the effects of noise. Specifically, We propose a modeling framework that integrates the representation of graph structure with textual information from LLMs to capture intricate user-item interactions. We also suggest an alignment paradigm to enhance representation performance by aligning semantic signals from LLMs and structural features from GNN models. Additionally, we introduce a contrastive learning scheme to relieve the impact of noise and improve model performance. Extensive experiments on public datasets demonstrate that our model consistently outperforms the state-of-the-art methods. DALR achieves improvements ranging from 2.82% to 12.20% in Recall@5 and from 1.04% to 3.48% in NDCG@5 compared to the strongest baseline model, using the Steam dataset as an example.

A novel fuzzy neural collaborative filtering for recommender systems

In collaborative filtering recommendations, part of studies mainly focus on quantitatively learning user preferences based on explicit rating information. However, due to the uncertainty and complexity of decision-making scenarios, user preferences usually express ambiguity and diversity. Therefore, to fully capture user preferences from both qualitative and quantitative perspectives and improve the accuracy and reliability of recommendations, we propose a novel fuzzy neural collaborative filtering for recommender systems. Firstly, we qualitatively divide user preferences into fine-grained categories based on picture fuzzy set and transform the rating matrix into four preference degree matrices. Then, we employ Bernoulli matrix factorization to independently learn preference features of each submatrix to obtain picture fuzzy numbers. To enhance the adaptability of picture fuzzy set in recommender systems, we design an improved scoring function based on picture fuzzy number to effectively distinguish differences in user preference levels. In addition, we use a simple deep neural framework to quantitatively extract global preferences of users and fuse it with fine-grained preferences of users to thoroughly predict user preferences. Experiments on four benchmark datasets show that the proposed model outperforms other comparison methods in terms of recommendation accuracy. Compared with the closest competitor method, our model has the highest improvements of 5.08% and 4.04% in the metrics HR@10 and NDCG@10, respectively.

On the Opportunities and Challenges of Offline Reinforcement Learning for Recommender Systems

Reinforcement learning serves as a potent tool for modeling dynamic user interests within recommender systems, garnering increasing research attention of late. However, a significant drawback persists: its poor data efficiency, stemming from its interactive nature. The training of reinforcement learning-based recommender systems demands expensive online interactions to amass adequate trajectories, essential for agents to learn user preferences. This inefficiency renders reinforcement learning-based recommender systems a formidable undertaking, necessitating the exploration of potential solutions. Recent strides in offline reinforcement learning present a new perspective. Offline reinforcement learning empowers agents to glean insights from offline datasets and deploy learned policies in online settings. Given that recommender systems possess extensive offline datasets, the framework of offline reinforcement learning aligns seamlessly. Despite being a burgeoning field, works centered on recommender systems utilizing offline reinforcement learning remain limited. This survey aims to introduce and delve into offline reinforcement learning within recommender systems, offering an inclusive review of existing literature in this domain. Furthermore, we strive to underscore prevalent challenges, opportunities, and future pathways, poised to propel research in this evolving field.

Boosting Healthiness Exposure in Category-Constrained Meal Recommendation Using Nutritional Standards

Food computing, a newly emerging topic, is closely linked to human life through computational methodologies. Meal recommendation, a food-related study about human health, aims to provide users a meal with courses constrained from specific categories (e.g., appetizers, main dishes) that can be enjoyed as a service. Historical interaction data, important user information, is often used by existing models to learn user preferences. However, if a user’s preferences favor less healthy meals, the model will follow that preference and make similar recommendations, potentially negatively impacting the user’s long-term health. This emphasizes the necessity for health-oriented and responsible meal recommendation systems. In this article, we propose a healthiness-aware and category-wise meal recommendation model called CateRec, which boosts healthiness exposure by using nutritional standards as knowledge to guide the model training. Two fundamental questions are raised and answered: (1) How can the healthiness of meals be evaluated? Two well-known nutritional standards from the World Health Organization and the United Kingdom Food Standards Agency are used to calculate the healthiness score of the meal. (2) How can the model training be guided in a health-oriented manner? We construct category-wise personalization partial rankings and category-wise healthiness partial rankings, and theoretically analyze that they meet the necessary properties and assumptions required to be trained by the maximum posterior estimator under Bayesian probability. The data analysis confirms the existence of user preferences leaning towards less healthy meals in two public datasets. A comprehensive experiment demonstrates that our CateRec effectively boosts healthiness exposure in terms of mean healthiness score and ranking exposure while being comparable to the state-of-the-art model in terms of recommendation accuracy.

Computational Optimisation of Urban Design Models: A Systematic Literature Review

The densification of urban spaces globally has contributed to a need for design tools supporting the planning of more sustainable, efficient, and liveable cities. Urban Design Optimisation (UDO) responds to this challenge by providing a means to explore many design solutions for a district, evaluate multiple objectives, and make informed selections from many Pareto-efficient solutions. UDO distinguishes itself from other forms of design optimisation by addressing the challenges of incorporating a wide range of planning goals, managing the complex interactions among various urban datasets, and considering the social–technical aspects of urban planning involving multiple stakeholders. Previous reviews focusing on specific topics within UDO do not sufficiently address these challenges. This PRISMA systematic literature review provides an overview of research on topics related to UDO from 2012 to 2022, with articles analysed across seven descriptive categories. This paper presents a discussion on the state-of-the-art and identified gaps present in each of the seven categories. Finally, this paper argues that additional research to improve the socio-technical understanding and usability of UDO would require: (i) methods of optimisation across multiple models, (ii) interfaces that address a multiplicity of stakeholders, (iii) exploration of frameworks for scenario building and backcasting, and (iv) advancing AI applications for UDO, including generalizable surrogates and user preference learning.

ReCRec: Reasoning the Causes of Implicit Feedback for Debiased Recommendation

Implicit feedback ( e.g ., user clicks) is widely used in building recommender systems (RS). However, the inherent notorious exposure bias significantly affects recommendation performance. Exposure bias refers a phenomenon that implicit feedback is influenced by user exposure, and does not precisely reflect user preference. Current methods for addressing exposure bias primarily reduce confidence in unclicked data, employ exposure models, or leverage propensity scores. Regrettably, these approaches often lead to biased estimations or elevated model variance, yielding sub-optimal results. To overcome these limitations, we propose a new method ReCRec that Re asons the C auses behind the implicit feedback for debiased Rec ommendation. ReCRec identifies three scenarios behind unclicked data — i.e. , unexposed, dislike or a combination of both. A reasoning module is employed to infer the category to which each instance pertains. Consequently, the model is capable of extracting reliable positive and negative signals from unclicked data, thereby facilitating more accurate learning of user preferences. We also conduct thorough theoretical analyses to demonstrate the debiased nature and low variance of ReCRec. Extensive experiments on both semi-synthetic and real-world datasets validate its superiority over state-of-the-art methods.

Channel-Enhanced Contrastive Cross-Domain Sequential Recommendation

Sequential recommendation help users find interesting items by modeling the dynamic user-item interaction sequences. Due to the data sparseness problem, cross-domain sequential recommendation (CDSR) are proposed. CDSR explore rich data from a source domain to improve performance of the target domain. However, most of the existing CDSR methods are difficult to capture the temporal context of sequences and only learn user preference based on interactions of single domain, which leads to suboptimal performance. To address these shortcomings, we propose a channel-enhanced contrastive cross-domain sequential recommendation model (C3DSR). To be specific, (1) we design a feature extractor, which extends attention to the channel dimension, to extract the user’s channel feature and capture the temporal contextual relationships between sequences. Then we calculate the weights of each channel by using three SE-Res2Blocks and multiply it with the channel feature to obtain user preference. (2) We concatenate the user’s single-domain representation, the cross-domain representation, and the user features to make CDSR. Contrastive learning is leveraged to enhance mutual information between two domains. Experimental results show that the proposed model achieves the significant improvement of performance compared with other CDSR models on Amazon and HVIDEO datasets.

Enhancing conversational recommendation systems through the integration of KNN with ConLinUCB contextual bandits

In recommender system research, contextual multi-armed bandits have shown promise in delivering tailored recommendations by utilizing contextual data. However, their effectiveness is often curtailed by the cold start problem, arising from the lack of initial user data. This necessitates extensive exploration to ascertain user preferences, consequently impeding the speed of learning. The advent of conversational recommendation systems offers a solution. Through these systems, the conversational contextual bandit algorithm swiftly learns user preferences for specific key-terms via interactive dialogues, thereby enhancing the learning pace. Despite these advancements, there are limitations in current methodologies. A primary issue is the suboptimal integration of data from key-term-centric dialogues and arm-level recommendations, which could otherwise expedite the learning process. Another crucial aspect is the strategic suggestion of exploratory key phrases. These phrases are essential in quickly uncovering users potential interests in various domains, thus accelerating the convergence of accurate user preference models. Addressing these challenges, the ConLinUCB framework emerges as a groundbreaking solution. It ingeniously combines feedback from both arm-level and key-term-level interactions, significantly optimizing the learning trajectory. Building upon this, the framework integrates a K-nearest neighbour (KNN) approach to refine key-term selection and arm recommendations. This integration hinges on the similarity of user preferences, further hastening the convergence of the parameter vectors.

Intelligent adaptive lighting algorithm: Integrating reinforcement learning and fuzzy logic for personalized interior lighting

The lighting requirements are subjective and one light setting cannot work for all. However, there is little work on developing smart lighting algorithms that can adapt to user preferences. To address this gap, this paper uses fuzzy logic and reinforcement learning to develop an adaptive lighting algorithm. In particular, we develop a baseline fuzzy inference system (FIS) using the domain knowledge, generating light recommendation based on a set of intuitive rules. These rules, derived from existing literature, are based on environmental conditions i.e. daily glare index, and user information including age, activity, and chronotype. Through a feedback mechanism, the user interacts with the algorithm, correcting the algorithm output to their preferences. We interpret these corrections as rewards to a Q-learning algorithm, which tunes the FIS parameters online to match the user preferences. The Q-learning is a model-free learning algorithm that learns to act optimally by interacting with the user and the rewards it receives. This allows the proposed algorithm to work in a model-free manner, effectively handling the uncertainties that might arise from the individualistic preferences of users. To the authors’ best knowledge, this algorithm is pioneering work in designing intelligent algorithms for personalized lighting control, featuring several elements of novelty, including the number of environmental and user-related inputs, the continuous control of light intensity as opposed to common on/off control, and the ability to learn user preferences. The algorithm is implemented in a real aircraft cabin and is evaluated in an extensive user study. The implementation results demonstrate that the developed algorithm possesses the capability to learn user preferences while successfully adapting to a wide range of environmental conditions and user characteristics. This underscores its viability as a potent solution for intelligent light management, featuring advanced learning capabilities.

A Hybrid Deep Learning Model Utilizing Cross-Structural Multi-Behavioral Comparative Recommendation for Sustainable Electric Transportation Infrastructure

Ensuring the sustainability of transportation infrastructure for electric vehicles (e-trans) is increasingly imperative in the pursuit of decarbonization goals and addressing the pressing energy shortage. By prioritizing the development and maintenance of resilient e-trans platforms through the optimization of the public charging network, electric vehicle businesses can effectively meet the needs of users, thereby contributing to efforts aimed at improving environmental quality. To achieve this goal, researching the dynamics of vehicle user behaviors plays a crucial role. In this paper, we propose cross-structure multi-behavior contrastive learning for recommendation (C-MBR), which takes into account the dynamic preferences of users, and develops model profiles from the global structure module, local structure module, cross-behavior contrastive learning module, cross-structure contrastive learning module, and model prediction and optimization. C-MBR is mainly designed to learn user preferences from the diversity of users’ behaviors in the process of interacting with the project, so as to grasp the different behavioral intentions of users. The experimental and analytical research is further conducted and validated for dealing with cold start problems. The results indicate that C-MBR has a strong ability to deal with the problem of sparse data. Compared with the ablation experiment, the model performance of C-MBR is significantly enhanced, showing that the C-MBR model can fully apply the information of a global structure and local structure in cross-structure comparative learning and multi-behavioral comparative learning to further alleviate the problem of data sparsity. As a result, the e-trans infrastructure will be significantly enhanced by addressing the issue of data-driven disruption.

Learning Time Slot Preferences via Mobility Tree for Next POI Recommendation

Next Point-of-Interests (POIs) recommendation task aims to provide a dynamic ranking of POIs based on users' current check-in trajectories. The recommendation performance of this task is contingent upon a comprehensive understanding of users' personalized behavioral patterns through Location-based Social Networks (LBSNs) data. While prior studies have adeptly captured sequential patterns and transitional relationships within users' check-in trajectories, a noticeable gap persists in devising a mechanism for discerning specialized behavioral patterns during distinct time slots, such as noon, afternoon, or evening. In this paper, we introduce an innovative data structure termed the ``Mobility Tree'', tailored for hierarchically describing users' check-in records. The Mobility Tree encompasses multi-granularity time slot nodes to learn user preferences across varying temporal periods. Meanwhile, we propose the Mobility Tree Network (MTNet), a multitask framework for personalized preference learning based on Mobility Trees. We develop a four-step node interaction operation to propagate feature information from the leaf nodes to the root node. Additionally, we adopt a multitask training strategy to push the model towards learning a robust representation. The comprehensive experimental results demonstrate the superiority of MTNet over eleven state-of-the-art next POI recommendation models across three real-world LBSN datasets, substantiating the efficacy of time slot preference learning facilitated by Mobility Tree.

Tail-STEAK: Improve Friend Recommendation for Tail Users via Self-Training Enhanced Knowledge Distillation

Graph neural networks (GNNs) are commonly employed in collaborative friend recommendation systems. Nevertheless, recent studies reveal a notable performance gap, particularly for users with limited connections, commonly known as tail users, in contrast to their counterparts with abundant connections (head users). Uniformly treating head and tail users poses two challenges for tail user preference learning: (C1) Label Sparsity, as tail users typically possess limited labels; and (C2) Neighborhood Sparsity, where tail users exhibit sparse observable friendships, leading to distinct preference distributions and performance degradation compared to head users. In response to these challenges, we introduce Tail-STEAK, an innovative framework that combines self-training with enhanced knowledge distillation for tail user representation learning. To address(C1), we present Tail-STEAK-base, a two-stage self-training framework. In the first stage, only head users and their accurate connections are utilized for training, while pseudo links are generated for tail users in the second stage. To tackle (C2), we propose two data augmentation-based self-knowledge distillation pretext tasks. These tasks are seamlessly integrated into different stages of Tail-STEAK-base, culminating in the comprehensive Tail-STEAK framework. Extensive experiments, conducted on state-of-the-art GNN-based friend recommendation models, substantiate the efficacy of Tail-STEAK in significantly improving tail user performance. Our code and data are publicly available at https://github.com/antman9914/Tail-STEAK.

Sentiment-Time Heterogeneous Residual Graph Attention Transformer for Session-Based Recommendation

Session-Based Recommendation (SBR) systems are facing considerable challenges, with their primary objective being to implement precise recommendations based on users’ historical behavior sequences. Graph Neural Networks (GNNs) have emerged as powerful tools for processing graph-structured data in recommendation systems. Although recent research has advanced in this area, a significant gap remains in the in-depth exploration of transitional relationships between user interests. Additionally, real-world recommendation scenarios typically involve various heterogeneous relationships, which contain a wealth of information that can significantly enhance the learning of user preferences. To address this research gap, in this paper, we introduce a model termed the Sentiment-Time Heterogeneous Residual Graph Attention Transformer (STH-ResGAT), which is designed to capture the dynamic nature of user interests and the complexity inherent in heterogeneous graphs. In STH-ResGAT, we develop a Sentiment-Time-Heterogeneous Graph (STH-Graph) that integrates sentiment and time factors into the edges of the graph structure. Furthermore, the Residual Graph Attention Transformer for Heterogeneous Networks (ResGAT-Het) is designed to manage diverse node and edge types based on the STH-Graph. Extensive experiments are conducted on four widely-used benchmark datasets: Ciao, Yelp, Epinions and LibraryThing. The results demonstrate that our proposed STH-ResGAT method significantly outperforms previous state-of-the-art baseline approaches.The implementation of ResGAT-Het is available in https://github.com/zhangyu2234/ResGAT-Het.git .

Explicit Behavior Interaction with Heterogeneous Graph for Multi-behavior Recommendation

Multi-behavior recommendation systems exploit multi-type user–item interactions (e.g., clicking, adding to cart and collecting) as auxiliary behaviors for user modeling, which can alleviate the problem of data sparsity faced by traditional recommendation systems. The key point of multi-behavior recommendation systems is to make full use of the auxiliary behavior information for the learning of user preferences. However, there are two challenges in existing methods that need to be explored: (1) capturing personalized user preferences based on multiple auxiliary behaviors, especially for negative feedback signals; and (2) explicitly modeling the semantics between auxiliary and target behaviors, and learning the explicit interactions between multiple behaviors. To tackle the two problems described above, we propose a novel model, called explicit behavior interaction with heterogeneous graph for multi-behavior recommendation (MB-EBIH). In particular, we first construct a heterogeneous behavior graph, including both positive and negative behaviors. A pre-trained model based on graph neural network (GNN) is then used to generate explicit behavior interaction values as the edge weights for the heterogeneous behavior graph. These weights reflect the importance of each of the auxiliary behaviors in an explicit manner. Finally, the extracted explicit behavior interaction information is incorporated into the multi-behavior user–item bipartite graphs to learn better representations. Experimental results on four real-world datasets demonstrate the effectiveness of our model in terms of exploring multi-behavioral data; and ablation and analysis experiments further demonstrate the effectiveness of explicit behavior interaction information.

Learning user preferences from Multi-Contextual Sequence influences for next POI recommendation

<abstract> <p>The recommendation of the next Point of Interest (POI) has attracted significant attention within the domain of POI recommendations in recent years. Existing methods for next POI recommendation are built on the original check-in sequences of users. Despite effectiveness, the original check-in sequences mix the influences of different contextual factors, which inevitably weakens the model ability of learning user preferences from the complex contextual information. To overcome this issue, we propose a novel Multi-Contextual Sequence-based Attention Network (MCSAN) for next POI recommendations. MCSAN first develops a new con-textual influence-based sampling strategy, which can transform the original check-in sequences into a series of contextual information-aware subsequences. Moreover, the constructed subsequences meticulously capture the impacts of various contextual information from the original check-in sequences. Then, MCSAN leverage the attention-based neural network to learn the representations of POIs from the generated subsequences. Finally, MCSAN develops a new feature fusion method that extracts user preferences from the learned POI presentations adaptively. Extensive experiments conducted on real-world datasets indicate the effectiveness of our proposed MCSAN for the next POI recommendation task, compared to recent representative methods.</p> </abstract>

Robust and efficient algorithms for conversational contextual bandit

Conversational contextual bandit is one of the notable variants of contextual bandit and it is shown to have superior performance in recommendation applications. The core idea of conversational contextual bandits utilizing is conversational feedback from users to improve the speed of learning user preference. We show that in real-world applications conversational feedback can be imbalanced and such feedback causes the latest conversational contextual bandit algorithm to conduct many conversations but has a slower learning speed than the baseline algorithm without conversational feedback. How to deal with imbalanced conversational feedback? How to schedule conversations across the learning horizon? In-depth analysis of the limitations of one representative conversational contextual bandit algorithm reveals insights to design ICF-UCB ((Imbalanced Conversational Feedback Upper Confidence Bound)) algorithm, which maintains a fast learning speed under imbalanced feedbacks. ICF-UCB achieves this by adaptively eliminating conversations that may slow down the learning speed. Furthermore, ICF-UCB adaptively schedules conversations to the decision rounds where suboptimal actions may trap the decision maker. It also adaptively selects appropriate conversations to avoid such traps. This algorithm is shown to have sublinear regret. Extensive experiments on synthetic datasets and public real-world datasets (from Yelp and TripAdvisor) validate the superior performance of ICF-UCB for recommendation tasks.

Learning Hierarchical Spatial Tasks with Visiting Relations for Next POI Recommendation

Sparsity is an established problem for the next Point-of-Interest (POI) recommendation task, where it hinders effective learning of user preferences from the User-POI matrix. However, learning multiple hierarchically related spatial tasks, and visiting relations between users and POIs, can help to alleviate this sparsity problem. In this article, we propose our Hierarchical Multi-Task Graph Recurrent Network (HMT-GRN) approach, which alleviates the sparsity problem by learning different User-Region matrices of lower sparsities in a multi-task setting. We then perform a Hierarchical Beam Search (HBS) on the different region and POI distributions to hierarchically reduce the search space with increasing spatial granularity and predict the next POI. Our HBS provides efficiency gains by reducing the search space, resulting in speedups of 5 to 7 times over an exhaustive approach. In addition, we propose a selectivity layer to predict if the next POI has been visited before by the user to balance between personalization and exploration. Further, we propose a novel Joint Triplet Loss Learning (JTLL) module to learn visited and unvisited relations between users and POIs for the recommendation task. Experimental results on two real-world Location-Based Social Network (LBSN) datasets show that our proposed approach significantly outperforms baseline and the state-of-the-art methods.

NRDL: Decentralized user preference learning for privacy-preserving next POI recommendation

Predicting where a user goes next in terms of his or her previously visited points of interest (POIs) is significant for facilitating users’ daily lives. Simultaneously, it must be acknowledged that the check-in and trajectory information of the user is absolutely disclosed to others in location-based social networks when recommending the next POIs. Therefore, how to achieve an accurate next POI recommendation on the premise of privacy preservation is a critical challenge. To address this challenge, we propose decentralized user preference learning for privacy-preserving next POI recommendation, called NRDL. First, to capture the user’s next POI preference, we model the user’s real-time demand representation by POI profile, POI category, absolute time, transition time and distance between previously visited POIs, which is input into an attention-based recurrent neural network (RNN) model for embedding. Second, to perform privacy preservation, we develop a decentralized learning framework that can achieve user preference learning by raw data on each user’s side. Learning on each user’s side can make the privacy data of the user not be revealed to platforms or others, and learning from raw data can guarantee the value of check-ins and further accuracy. Finally, we evaluate the proposed model on two widely used Gowalla and Foursquare datasets, and the improvements over the state-of-the-art model are 25.00% and 9.95% at recall@1 and NDCG@1 on Gowalla as well as 22.51% and 10.59% on Foursquare.

Enhancing conversational recommender systems via multi-level knowledge modeling with semantic relations

Augmenting conversational recommendation systems (CRS) with prior knowledge is crucial for learning user preferences and understanding contextual semantics. Existing methods are mainly based on knowledge graphs (KG), which rely on relationship information between entities, ignoring the semantic relationship in the dialogue. In addition, due to the limited information reflected by structured knowledge in KG, they still need broader external knowledge support to understand contextual semantics.To address the above issues, we propose a knowledge prompt-based CRS named MKCRS, which utilizes semantic relations to model multi-level knowledge and integrate it into CRS sub-tasks. Specifically, we first derive multi-level knowledge representations related to the current dialogue from external knowledge and then perform deep explicit and implicit modeling to construct knowledge prompts. To implement this framework, we design a semantic fusion model based on named entity phrases and a unified knowledge prompt generator. The former exploits explicit semantic relations between entities and contexts to enhance knowledge representations, while the latter adaptively learns the most important knowledge prompts via implicit connections between knowledge. Finally, based on the generated knowledge prompts, we construct knowledge-enhanced prompt templates for recommendation and dialogue generation tasks. Experimental results on the two datasets demonstrate that MKCRS outperforms the state-of-the-art models.

Causal Inference for Knowledge Graph Based Recommendation

Knowledge Graph (KG), as a side-information, tends to be utilized to supplement the collaborative filtering (CF) based recommendation model. By mapping items with the entities in KGs, prior studies mostly extract the knowledge information from the KGs and inject it into the representations of users and items. Despite their remarkable performance, they fail to model the user preference on attribute in the KG, since they ignore that (1) the structure information of KG may hinder the user preference learning, and (2) the user's interacted attributes will result in the bias issue on the similarity scores. With the help of causality tools, we construct the causal-effect relation between the variables in KG-based recommendation and identify the reasons causing the mentioned challenges. Accordingly, we develop a new framework, termed Knowledge Graph-based Causal Recommendation (KGCR), which implements the deconfounded user preference learning and adopts counterfactual inference to eliminate bias in the similarity scoring. Ultimately, we evaluate our proposed model on three datasets, including Amazon-book, LastFM, and Yelp2018 datasets. By conducting extensive experiments on the datasets, we demonstrate that KGCR outperforms several state-of-the-art baselines, such as KGNN-LS [1], KGAT [2] and KGIN [3]. We release our codes in the public domain: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/weiyinwei/KGCR</uri> .