With the rapid growth of multi-modal content on the Web, robust vision-language models are essential for semantic understanding and classification of web images under diverse and dynamic contexts, supporting Web applications such as multimedia search and recommendation. Prompt learning has proven effective for enhancing vision-language models in semantic image classification tasks. However, previous methods often suffer from poor generalization: the learned prompts tend to overfit the base classes seen during training, leading to poor performance on unseen classes and under distribution shifts. This issue is especially challenging in Web-scale data, where new classes emerge and distributions shift dynamically. To address these limitations, we propose PLIKD, a novel prompt learning method that integrates instance-aware knowledge distillation for robust Web-scale semantic image classification. Specifically, PLIKD introduces an instance-aware knowledge extraction module, which leverages multi-modal large language models through a step-by-step strategy to extract external knowledge for each image instance. To incorporate this extracted knowledge, PLIKD further introduces an instance-aware knowledge distillation module, which consists of two key steps: (1) a dual-teacher strategy for robust and informative knowledge distillation, and (2) fine-grained cross-modal alignment via Smooth and Sparse Optimal Transport. Extensive experiments demonstrate that PLIKD significantly improves generalization to both seen and unseen classes, and remains robust under distribution shifts, outperforming existing state-of-the-art methods on Web-scale semantic image classification.

Hash-based collaborative filtering (Hash-CF) approaches recently employ efficient Hamming distance of learned binary representations to accelerate recommendations. Benefiting from its probabilistic nature, Variational Autoencoder (VAE) enables robust Hash-CF with stronger generalization ability. However, VAE-based Hash-CF still faces two challenging problems: 1) Traditional VAE urges the latent variables of different users (or items) to fit a unified and monotonous prior distribution, and lacks considerations for distinctive characteristics of users (or items). The obtained representations of users and items with slight individual differentiation may further weaken the performance of Hash-CF for subsequent personalized recommendations. 2) Hash-CF under the VAE framework requires discrete optimization on latent Bernoulli distributions, which are discrete and NP-hard to optimize. In this paper, we propose a Dual Discrete Collaborative Filtering (DDCF) approach, including a cluster-enhanced representation generation module and a CNF-enabled discrete optimization module. The former module mainly develops cluster-aware latent space to generate discriminative representations for users or items with significantly different characteristics. The latter module employs Continuous Normalizing Flow (CNF) to achieve discrete optimization on latent Bernoulli distributions steadily and effectively. Extensive experiments conducted on multiple real-world datasets demonstrate the superiority of our DDCF compared with the state-of-art methods in terms of effectiveness and efficiency.

Cross-Domain Recommendation (CDR) has been widely investi- gated for solving long-standing data sparsity problem via knowl- edge sharing across domains. In this paper, we focus on the Multi- Modal Cross-Domain Recommendation (MMCDR) problem where different items have multi-modal information while few users are overlapped across domains. MMCDR is particularly challenging in two aspects: fully exploiting diverse multi-modal information within each domain and leveraging useful knowledge transfer across domains. However, previous methods fail to cluster items with similar characteristics while filtering out inherit noises within different modalities, hurdling the model performance. What is worse, conventional CDR models primarily rely on overlapped users for domain adaptation, making them ill-equipped to handle scenarios where the majority of users are non-overlapped. To fill this gap, we propose Joint Similarity Item Exploration and Overlapped User Guidance (SIEOUG) for solving the MMCDR problem. SIEOUG first proposes similarity item exploration module, which not only obtains pair-wise and group-wise item-item graph knowledge, but also reduces irrelevant noise for multi-modal modeling. Then SIEOUG proposes user-item collaborative filtering module to aggregate user/item embeddings with the attention mechanism for collaborative filtering. Finally SIEOUG proposes overlapped user guidance module with optimal user matching for knowledge sharing across domains. Our empirical study on Amazon dataset with several different tasks demonstrates that SIEOUG significantly outperforms the state-of-the-art models under the MMCDR setting.

Next Point-of-Interest (POI) recommendation has become a crucial task in Location-Based Social Networks (LBSNs), which provide personalized recommendations by predicting the user's next check-in locations. Commonly used models including Recurrent Neural Networks (RNNs) and Graph Convolutional Networks (GCNs) have been widely explored. However, these models face significant challenges, including the difficulty of capturing the hierarchical and tree-like structure of POIs in Euclidean space and the sparsity problem inherent in POI recommendations. To address these challenges, we propose a Hyperbolic Variational Graph Auto-Encoder (HVGAE) for next POI recommendation. Specifically, we utilize a Hyperbolic Graph Convolutional Network (Hyperbolic GCN) to model hierarchical structures and tree-like relationships by converting node embeddings from euclidean space to hyperbolic space. Then we use Variational Graph Auto-Encoder (VGAE) to convert node embeddings to probabilistic distributions, enhancing the capture of deeper latent features and providing a more robust model structure. Furthermore, we combine the Mamba4Rec recommender and Rotary Position Embedding (RoPE) and propose Rotary Position Mamba (RPMamba) to effectively utilize POI embeddings rich in sequential information, which improves the accuracy of the next POI recommendation. Extensive experiments on three public datasets demonstrate the superior performance of the HVGAE model.

This article has been retracted: please see Elsevier policy on article withdrawal ( https://www.elsevier.com/about/policies-and-standards/article-withdrawal ). This article has been retracted at the request of the authors. The authors reported critical technical concerns caused by the ignored parameter Θ (a dynamic threshold that controls the specific privacy requirements of the used dataset) in the experiment evaluation process. Therefore, the authors requested retraction, and the Editors agreed with this request. The authors regret the error.

Personalized incentives are crucial for boosting user engagement and increasing platform revenues. Many studies have utilized uplift modeling to estimate the conditional average treatment effects (CATEs) of incentives and then allocate them under cost constraints. However, identifying which users should receive such incentives remains challenging, posing a selection bias problem. Traditional representation-based approaches mitigate bias by balancing treated and controlled distributions but overlook local similarity information. Recognizing that similar users should exhibit similar outcomes, it is vital to preserve both intra-similarity within treatment groups and inter-similarity between covariate and representation spaces. Moreover, existing methods primarily focus on CATE accuracy, neglecting the ranking ability vital for uplift modeling. We propose the Similarity Preserved Counterfactual Incentive Effect Estimation ( S-CIEE ) method, comprising three modules: (1) an Intra-Similarity Preservation Regularizer via Fused Gromov-Wasserstein Optimal Transport, (2) an Inter-Similarity Preservation Regularizer using a similarity constraint, and (3) a Rank-Aware Learning module for uplift ranking. Comprehensive experiments on one semi-synthetic and two real-world datasets show that S-CIEE improves both CATE accuracy and uplift modeling performance.

Estimating individual treatment effects (ITE) from observational data is challenging due to the absence of counterfactuals and the treatment selection bias. Prevalent ITE estimation methods tackle these challenges by aligning the treated and controlled distributions in the representational space. However, two critical issues have long been overlooked: (1)Mini-batch sampling sensitivity (MSS) issue, where representation distribution alignment at a mini-batch level is vulnerable to poor sampling cases, such as data imbalance and outliers; (2)Inconsistent representation learning (IRL) issue, where representation learning within a unified backbone network suffers from inconsistent gradient update directions due to the distribution skew between different treatment groups. To resolve these issues, we propose CE-RCFR, a Robust CounterFactual Regression framework for Consensus-Enabled causal effect estimation, including a relaxed distribution discrepancy regularizer (RDDR) module and a consensus-enabled aggregator (CEA) module. Specifically, for the robust representation alignment perspective, RDDR addresses the MSS issue by minimizing unbalanced optimal transport divergence between different treatment groups with a relaxed marginal constraint. For the accurate representation optimization perspective, CEA addresses the IRL issue by resolving the consistent gradient update directions on shared parameters within the backbone network. Extensive experiments demonstrate that CE-RCFR significantly outperforms the state-of-the-art methods in treatment effect estimations.

User cold-start recommendation aims to provide accurate items for the newly joint users and is a hot and challenging problem. Nowadays as people participant in different domains, how to recommend items in the new domain for users in an old domain has become more urgent. In this paper, we focus on the Dual Cold-Start Cross Domain Recommendation (Dual-CSCDR) problem. That is, providing the most relevant items for new users on the source and target domains. The prime task in Dual-CSCDR is to properly model user-item rating interactions and map user expressive embeddings across domains. However, previous approaches cannot solve Dual-CSCDR well, since they separate the collaborative filtering and distribution mapping process, leading to the error superimposition issue. Moreover, most of these methods fail to fully exploit the cross-domain relationship among large number of non-overlapped users, which strongly limits their performance. To fill this gap, we propose User Distribution Mapping model with Collaborative Filtering (UDMCF), a novel end-to-end cold-start cross-domain recommendation framework for the Dual-CSCDR problem. UDMCF includes two main modules, i.e., rating prediction module and distribution alignment module. The former module adopts one-hot ID vectors and multi-hot historical ratings for collaborative filtering via a contrastive loss. The latter module contains overlapped user embedding alignment and general user subgroup distribution alignment. Specifically, we innovatively propose unbalance distribution optimal transport with typical subgroup discovering algorithm to map the whole user distributions. Our empirical study on several datasets demonstrates that UDMCF significantly outperforms the state-of-the-art models under the Dual-CSCDR setting.

With the continuous accumulation of users' check-in data, we can gradually capture users' behavior patterns and mine users' preferences. Based on this, the next point-of-interest (POI) recommendation has attracted considerable attention. Its main purpose is to simulate users' behavior habits of check-in behavior. Then, different types of context information are used to construct a personalized recommendation model. However, the users' check-in data are extremely sparse, which leads to low performance in personalized model training using recurrent neural network. Therefore, we propose a category-aware gated recurrent unit (GRU) model to mitigate the negative impact of sparse check-in data, capture long-range dependence between user check-ins and get better recommendation results of POI category. We combine the spatiotemporal information of check-in data and take the POI category as users' preference to train the model. Also, we develop an attention-based category-aware GRU (ATCA-GRU) model for the next POI category recommendation. The ATCA-GRU model can selectively utilize the attention mechanism to pay attention to the relevant historical check-in trajectories in the check-in sequence. We evaluate ATCA-GRU using a real-world data set, named Foursquare. The experimental results indicate that our ATCA-GRU model outperforms the existing similar methods for next POI recommendation.

The ever-increasing popularity of the recommender system provides a convenient way for users to find their interesting items among plenty of candidate services. However, on account of the enhancement of user privacy protection consciousness in recent years, users tend to conceal their evaluation information from the public. Thus, a large number of users with little explicit rating information are generated (i.e., cold-start users), which makes it challenging to implement high-quality recommendations. It has become a serious barrier to further and broader applications of the recommender system. In response to this issue, we take social network information into account and first propose TeCF (Trust-enhanced Collaborative Filtering). Our proposal integrates user-based, item-based, and trust-based collaborative filtering methods harmoniously and achieves a good trade-off between privacy preservation and service recommendation accuracy. A case study is conducted to validate the feasibility and comprehensiveness of our research.