Preference Logical Reasoning with Preference Operators for Explainable Recommendations

Trust is one of the most critical quality factors for service requestors when they select the services from a large pool of Web services. However, existing web service trust models either do not focus on satisfying user's preferences for different quality of service (QoS) attributes, or do not pay enough attention to the impact of malicious ratings on trust evaluation. To address these gaps, a user-oriented trust model considering user's preferences and false ratings is proposed in this paper. The model introduces an approach to automatically mine user's preferences from their requirements, the preferences are used to determine the weights of each QoS attribute when integrating local trust into the multi-dimensional QoS attributes. The local trust on a service for the user is derived by combining the trust on QoS attributes and the trust on user's ratings. In this model, the users are classified into different groups according to their preferences, the honesty of each group is assessed by filtering out dishonest users using a hybrid approach which combines rating consistency clustering and an average method. To calculate the global trustworthiness of a service for the users group, the weight of ratings is dynamically adjusted according to the results of honesty assessment. The simulation results indicate that the model works well on personalized evaluation of trust, and it can effectively dilute the influence of malicious ratings.

The use of social robots in the domestic environment has increased during the past few decades. These robots are intended to maintain long-term interactions with humans while involving in a variety of tasks including daily activities, entertainment, and assisting elderly or disabled people. The ability to learn user's preferences and adapting interaction accordingly is a must for such robots. As the domestic environment consists of non-experts, social robots must possess more natural and human-friendly interaction capabilities. This paper presents an Autobiographical Memory(AM) based intelligent system which can learn user preferences through natural interactions and provide user adaptive services for each user in the multi-user domestic environment. The system is capable of learning user's preferences from hislher own statements and from another person's statements. Furthermore, the system is capable of adapting to user's hidden preference and changes of preferences easily. The robot's memory has been structured in such a way that it can easily remember the user groups and the relationship between users. This facilitates the robot for learning preferences which are common to a group of users. The system has been tested and validated using snack and beverage suggestion scenario.

A heterogeneous graph neural network model for list recommendation

Predicting the next interaction of a short-term interaction session is a challenging task in session-based recommendation. Almost all existing works rely on item transition patterns, and neglect the impact of user historical sessions while modeling user preference, which often leads to non-personalized recommendation. Additionally, existing personalized session-based recommenders capture user preference only based on the sessions of the current user, but ignore the useful item-transition patterns from other user's historical sessions. To address these issues, we propose a novel Heterogeneous Global Graph Neural Networks (HG-GNN) to exploit the item transitions over all sessions in a subtle manner for better inferring user preference from the current and historical sessions. To effectively exploit the item transitions over all sessions from users, we propose a novel heterogeneous global graph that contains item transitions of sessions, user-item interactions and global co-occurrence items. Moreover, to capture user preference from sessions comprehensively, we propose to learn two levels of user representations from the global graph via two graph augmented preference encoders. Specifically, we design a novel heterogeneous graph neural network (HGNN) on the heterogeneous global graph to learn the long-term user preference and item representations with rich semantics. Based on the HGNN, we propose the Current Preference Encoder and the Historical Preference Encoder to capture the different levels of user preference from the current and historical sessions, respectively. To achieve personalized recommendation, we integrate the representations of the user current preference and historical interests to generate the final user preference representation. Extensive experimental results on three real-world datasets show that our model outperforms other state-of-the-art methods.

Top-N recommendation, which aims to learn user ranking-based preference, has long been a fundamental problem in a wide range of applications. Traditional models usually motivate themselves by designing complex or tailored architectures based on different assumptions. However, the training data of recommender system can be extremely sparse and imbalanced, which poses great challenges for boosting the recommendation performance. To alleviate this problem, in this paper, we propose to reformulate the recommendation task within the causal inference framework, which enables us to counterfactually simulate user ranking-based preferences to handle the data scarce problem. The core of our model lies in the counterfactual question: "what would be the user's decision if the recommended items had been different?''. To answer this question, we firstly formulate the recommendation process with a series of structural equation models (SEMs), whose parameters are optimized based on the observed data. Then, we actively indicate many recommendation lists (called intervention in the causal inference terminology) which are not recorded in the dataset, and simulate user feedback according to the learned SEMs for generating new training samples. Instead of randomly intervening on the recommendation list, we design a learning-based method to discover more informative training samples. Considering that the learned SEMs can be not perfect, we, at last, theoretically analyze the relation between the number of generated samples and the model prediction error, based on which a heuristic method is designed to control the negative effect brought by the prediction error. Extensive experiments are conducted based on both synthetic and real-world datasets to demonstrate the effectiveness of our framework.

Pair-wise ranking based preference learning for points-of-interest recommendation

The incompleteness and uncertainty about the state of the world and about the consequences of actions are unavoidable. If we want to predict the performance of multiuser computing systems, we have the uncertainty of what the users are going to do, and how that affects system performance. Intelligent interface agent development is one way to mitigate the uncertainty about user behaviors by predicting what users will do based on learned users' behaviors, preferences, and intentions. This work focuses on developing user models that can analyze and predict user behavior in multi-agent systems. We have developed a formal theory of user behavior prediction based on hidden Markov models. This work learns the user model through a time-series action analysis and abstraction by taking users' preferences and intentions into account in order to formally define user modeling.

Learning user preferences by modeling historical purchase behaviors has significantly succeeded in existing recommender systems. Most use trained models to make predictions for users, and they assume that the training data samples and test data sample sets come from the same distribution. However, in practical applications, the distribution of users’ true preferences may be more complicated, and data drift can easily make the trained model invalid on the test dataset. In this case, to accurately model user preferences based on their historical behavior, two difficulties need to be addressed. First, it is difficult to model various purchase behavior shift situations due to their complexity. Second, inferring users’ true preferences from the complicated shifting cases is challenging. To solve the above problems, we build a robust recommender system to predict possible user purchase shifts and make recommendations for users. First, we propose a simulating strategy to cover possible scenarios when user purchase behavior shifts. Second, we build a novel voting framework to ensure the robustness of predicting results based on learned preferences. Extensive experiments were conducted, and the results demonstrate the outstanding performance of the proposed method on MovieLens-1M and LastFM datasets, providing at most 37.31% and 30.95% relative performance gains, respectively.

Invariant user preference learning is a core task in recommender systems. Accurately modeling user preferences is crucial, as it directly impacts the quality of recommendations. However, heterogeneous user preferences in feedback data often exhibit mixture distributions, which obscure invariant preferences and introduce bias. Existing methods typically address this issue by partitioning feedback data into multiple environments and learning invariant preferences across them. Nonetheless, these approaches often lack theoretical guarantees for environment construction and fail to capture the dynamic nature of user preferences across different environments. Along these lines, we propose a novel framework, Invariant and Environment-specific Preferences for unbiased recommendation (IEPref). IEPref leverages auxiliary information as a reliable signal to guide the environment classifier in partitioning the environment, thereby enabling the learning of more stable and generalizable user preference with theoretical guarantees. Additionally, we design environment-specific proxy modules to capture context-dependent preference patterns unique to each environment. The environment classifier assigns each user-item interaction to its corresponding latent environment, and both invariant and environment-specific preferences are integrated for recommendations. Extensive experiments on five real-world datasets demonstrate that IEPref achieves superior performance over existing baselines, effectively mitigating recommendation bias while preserving personalized modeling capabilities.

ExUP recommendations: Inferring user's product metadata preferences from single-criterion rating systems

Knowledge is a vital component of organizational success embedded within the human resources of a firm (Grant, 1996). Knowledge is lost by organizations when it is not used or when knowledgeable individuals turnover. Knowledge Management Systems (KMS) are designed to help organizations capture, store, distill, and distribute knowledge embedded within their employees. The effectiveness of KMS is dependent on individual learning and individual-specific learning preferences. Furthermore, as the world becomes more globalized and the job candidate pool from which organizations hire becomes more culturally diverse, the extent to which western models of organizational behavior hold becomes less clear. Using a multi-national survey, this study aims to determine to what extent learning preferences are dependent on culture. If learning preferences are dependent on culture, KMS designs that ignore culture may result in incomplete or ineffective knowledge transfer and learning outcomes. Our findings contribute to the KMS literature by suggesting that KMS design should be conducted with the goal of effectively facilitating learning across cultures. Specific KMS design recommendations include incorporating group activities and providing more flexibility, depending on the culturally derived learning preferences of specific users.

Large language model (LLM) agents have emerged as a promising solution for enhancing recommendation systems via user simulation. However, existing studies predominantly resort to prompt-based simulation using frozen LLMs, which frequently results in suboptimal item modeling and user preference learning, thereby ultimately constraining recommendation performance. To address these challenges, we introduce VRAgent-R1, a novel agent-based paradigm that incorporates human-like intelligence in user simulation. Specifically, VRAgent-R1 comprises two distinct agents: the Item Perception (IP) Agent and the User Simulation (US) Agent, designed for interactive user-item modeling. Firstly, the IP Agent emulates human-like progressive thinking based on MLLMs, effectively capturing hidden recommendation semantics in videos. With a more comprehensive multimodal content understanding provided by the IP Agent, the video recommendation system is equipped to provide higher-quality candidate items. Subsequently, the US Agent refines the recommended video sets based on in-depth chain-of-thought (CoT) reasoning and achieves better alignment with real user preferences through reinforcement learning. Experimental results on a large-scale video recommendation benchmark MicroLens-100k have demonstrated the effectiveness of our proposed VRAgent-R1 method, e.g., the IP Agent achieves a 6.0% improvement in NDCG@10, while the US Agent shows approximately 45.0% higher accuracy in user decision simulation compared to state-of-the-art baselines.

Cross-domain recommendation (CDR) aims to suggest items from new domains that align with potential user preferences, based on their historical interactions. Existing methods primarily focus on acquiring item representations by discovering user preferences under specific, yet possibly redundant, item features. However, user preferences may be more strongly associated with interacted items at higher semantic levels, rather than specific item features. Consequently, this item feature-focused recommendation approach can easily become suboptimal or even obsolete when conducting CDR with disturbances of these redundant features. In this paper, we propose a novel Preference Prototype-Aware (PPA) learning method to quantitatively learn user preferences while minimizing disturbances from the source domain. The PPA framework consists of two complementary components: a mix-encoder and a preference prototype-aware decoder, forming an end-to-end unified framework suitable for various real-world scenarios. The mix-encoder employs a mix-network to learn better general representations of interacted items and capture the intrinsic relationships between items across different domains. The preference prototype-aware decoder implements a learnable prototype matching mechanism to quantitatively perceive user preferences, which can accurately capture user preferences at a higher semantic level. This decoder can also avoid disturbances caused by item features from the source domain. The experimental results on public benchmark datasets in different scenarios demonstrate the superiority of the proposed PPA learning method compared to state-of-the-art counterparts. PPA excels not only in providing accurate recommendations but also in offering reliable preference prototypes. Our code is available at https://github.com/zyx-nuaa/PPA-for-CDR.

Customized path recommendation aims to provide personalized routing solutions that reflect individual user preferences, which is crucial for improving the travel experience across diverse user groups. Users’ path choices are influenced by a variety of factors, which are complex and interrelated. In this paper, we employ neural networks to model these intricate preferences and develop a customized path recommendation method. First, we extract users’ routing preferences from historical trajectory data. Then, we design neural networks to learn user preferences, with GRUs to predict sequential patterns. Finally, we propose a personalized weighted Dijkstra algorithm to generate customized paths for each user based on learned preferences. Case studies are conducted using a real trajectory data set. The results demonstrate that, compared to shortest path algorithms and frequency-based path selection methods, the proposed method can better fit users’ real path choices, showcasing its effectiveness in generating personalized routing solutions.

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.