Sequential recommendation has become a hot topic, which aims to predict the desired items for each user based on his/her historical actions. The mainstream advancements for this task focus on modeling user behaviors in a pure item ID-based manner, which often fail to provide satisfactory results due to data sparsity and cold-start issues. Recently, several studies that leverage multi-modal information (i.e., multi-modal sequential recommendation) have shed light on alleviating such issues. However, we argue that three limitations are still not well addressed: 1) they usually extract ID modality features of an item with an one-hot encoding, which does not include any semantic information; 2) they fail to effectively mitigate the semantic gap issue and explicitly explore the asynchronous interplay between any two modalities; and 3) during the model prediction stage, they neglect the significance of adaptively fusing multi-modal embeddings for each user. To address such defects, we propose a novel framework for multi-modal sequential recommendation, namely, a multi-way cascade-attention network (MCN). Specifically, we apply a lightweight graph propagation network to derive informative representations of the ID-oriented modality, explicitly encoding collaborative signals in the user-item interaction graph. Next, we develop a multi-way cascade-attention module (CAM) to accomplish user behavior sequence alignment across different modality spaces. Each CAM consists of a cross-attention block followed by a series of self-attention blocks. The former encodes the asynchronous interplay between two modalities, while the latter captures intra-modal temporal dependencies. Finally, we design a modality-aware attentive strategy to dynamically fuse the user's dynamic interests across different modality spaces. Our extensive experiments on four public datasets demonstrate the superiority of MCN over recent state-of-the-art recommenders.

Recently, graph contrastive learning (GCL) has attracted considerable attention in social recommendation, owing to its ability to enhance the robustness of node embedding learning against noise and data sparsity. Despite their effectiveness, we argue that existing GCL-based methods remain limited by three key issues: (1) during graph propagation, they rely on uniform neighbor aggregation and non-adaptive embedding readout, leading to suboptimal node representations; (2) when constructing contrastive views, they typically adopt graph augmentations based on stochastic perturbations of graph-structured data, which may undermine model fidelity; (3) during model optimization, they treat all observed instances equally, forgoing the subtle difference of each positive sample at different training periods. To address these limitations, we propose an effective and efficient GCL framework (EGCL) for social recommendation. Specifically, we devise a graph adaptive propagation module to learn informative embeddings of all items and users. Furthermore, we devise an augmentation-free dual CL paradigm, which consists of intra-CL within a single domain and inter-CL between two separate domains. In addition, we develop a self-adaptive weighted supervised learning paradigm and formulate the whole training procedure as a bi-level optimization problem. Extensive experiments are performed on four benchmarks, demonstrating the effectiveness and efficiency of EGCL over recent state-of-the-art recommenders. Our implementation and datasets are available at https://github.com/wubinzzu/EGCL .

Pre-trained Vision-Language Models (VLMs) require Continual Learning (CL) to efficiently update their knowledge and adapt to various downstream tasks without retraining from scratch. However, for VLMs, in addition to the loss of knowledge previously learned from downstream tasks, pre-training knowledge is also corrupted during continual fine-tuning. This issue is exacerbated by the unavailability of original pre-training data, leaving VLM’s generalization ability degrading. In this paper, we propose GIFT, a novel continual fine-tuning approach that utilizes synthetic data to overcome catastrophic forgetting in VLMs. Taking advantage of recent advances in text-to-image synthesis, we employ a pre-trained diffusion model to recreate both pre-training and learned downstream task data. In this way, the VLM can revisit previous knowledge through distillation on matching diffusion-generated images and corresponding text prompts. Leveraging the broad distribution and high alignment between synthetic image-text pairs in VLM’s feature space, we propose a contrastive distillation loss along with an image-text alignment constraint. To further combat in-distribution overfitting and enhance distillation performance with limited amount of generated data, we incorporate adaptive weight consolidation, utilizing Fisher information from these synthetic image-text pairs and achieving a better stability-plasticity balance. Extensive experiments demonstrate that our method consistently outperforms previous state-of-the-art approaches across various settings.

Next-item recommendation has received considerable attention in academia and industry, which aims to predict the next desired item for each user based on his historical behaviors. It has been validated that user behaviors are driven by two key factors:social influence, which leverages social relationships to better infer user preference, andsequential influence, which captures item transition patterns to model the dynamic evolution of user interest. While previous next-item recommenders have made great progress, we argue that there still exist three critical limitations: (1) they always follow the paradigm of entangling social and sequential influences, resulting in poor interpretability; (2) they fail to explicitly capture high-order influences at social-level and sequential-level, resulting in the suboptimal performance; (3) they fail to dynamically distinguish the importance of each influence factor when predicting user preference. To settle these three defects, we contribute a novel solution for socially-aware next-item recommendation, namely Disentangled Graph Contrastive Learning (DGCL) method, which explicitly disentangles social and sequential influences on user behavior data. Specifically, we first reorganize social relationships and all users' behavior sequences as two separate graphs. Then, a disentangled graph propagation module is developed on these two graphs to independently capture high-order influences at social-level and sequential-level. Furthermore, we formalize a dual contrastive learning paradigm as an auxiliary task to supervise the thorough disentanglement. Finally, we devise a user-specific attention mechanism to adaptively differentiate the importance of each influence factor for model prediction. Empirical results on four benchmark datasets demonstrate the superiority of DGCL over recent state-of-the-art recommenders. Further analysis verifies the rationality and necessity of each part in our solution. Our implemented codes and used datasets are available athttps://github.com/wubinzzu/DGCL.

Truth discovery is an effective tool for discovering the truth from a multitude of data points of varying quality, which inherently involves privacy concerns. While existing studies have predominantly focused on protecting workers’ submitted sensing data using local differential privacy (LDP), they overlook a crucial aspect of real-world scenarios: workers are likely to provide more accurate data for tasks they perceive as important, resulting in submissions that more closely approximate the truth for these tasks. Moreover, the prevalent use of the Laplace mechanism for noise addition, due to the inherent randomness and unboundedness of the Laplace distribution, might lead to excessive noise, potentially compromising the accuracy of truth discovery and yielding a noisy approximation of the truth. To address these limitations, we propose a Gaussian distribution-based truth discOvery approach under Local Differential privacy (GOLD). The algorithm’s core innovation lies in its comprehensive utilization of Gaussian distribution for both task importance and worker quality after adding Laplacian noise. Workers first apply Laplacian noise to their data locally, after which the problem is formalized as a constraint optimization task, deriving an iterative equation for the noisy truth. Theoretical analysis demonstrates that the GOLD algorithm rigorously adheres to local differential privacy requirements while achieving high truth accuracy and low time complexity. Empirical validation on two real datasets reveals that, compared to state-of-the-art algorithms, the GOLD algorithm improves the truth accuracy by at least 20%.

Task allocation, a core component of mobile crowd-sensing systems, facilitates the collection, analysis, and sharing of diverse data. While existing studies often employ planar Laplacian (PL) distribution to achieve Geo-indistinguishability (Geo-I) for worker location protection, the randomness and boundlessness of PL distribution, coupled with greedy allocation strategies, often lead to excessive noise and incomplete task assignments. Moreover, these approaches typically overlook the equilibrium between worker and server benefits. To address these challenges under Geo-I, we present the Kitty approach, which adopts Q-learning to achieve superior task allocation after formalizing a constrained optimization problem that maximizes profits for both parties. Kitty operates through three key mechanisms: 1) formalizing a constrained optimization problem based on a comprehensive analysis of both parties’ profits and a pre-defined equilibrium parameter, 2) implementing adaptive adjustment of the Q-learning greedy parameter to balance exploration and exploitation, and 3) designing two conflict resolution strategies to mitigate potential distance conflicts after location perturbation. Experiments on two real-world datasets demonstrate that Kitty outperforms the state-of-the-art by at least 15% in average travel distance reduction and 1% in task completion rate improvement.

Recommender systems aim at helping users to discover interesting items and assisting business owners to obtain more profits. Nonetheless, traditional recommendations fail to explore the varying importance of product characteristics for different product domains. In light of this, we propose a novel probabilistic model for recommendation, which could learn products’ characteristics in a fine-grained manner. Specifically, a user’s preference for a given product is modeled as a combination of visual and functional aspects. To make our method practical in large-scale industrial scenarios, we devise a computationally efficient learning algorithm to optimize VFPMF’s parameters. Experiments on four real-world datasets demonstrate the effectiveness and efficiency of our solution, compared with several state-of-the-art methods.

Modeling sequential behaviors is the core of sequential recommendation. As users visit items in chronological order, existing methods typically capture a user's present interests from his/her past-to-present behaviors, i.e., making recommendations with only the unidirectional past information. This article argues that future information is another critical factor for the sequential recommendation. However, directly learning from future-to-present behaviors inevitably causes data leakage. Here, it is pointed out that future information can be learned from users' collaborative behaviors. Toward this end, this article introduces sequential graphs to depict item transition relationships: where and how each item transits from and will transit to. This temporal evolution information is called the light cone in special and general relativity. Then, a bidirectional sequential graph convolutional network (BiSGCN) is proposed to learn item representations by encoding past and future light cones. Finally, a manifold translating embedding (MTE) method is proposed to model item transition patterns in Riemannian manifolds, which helps to better capture the geometric structures of light cones and item transition patterns. Experimental comparisons and ablation studies verify the outstanding performance of BiSGCN, the benefits of learning from the future, and the improvements of learning in Riemannian manifolds.

Next-item recommendation has been a hot research topic in academia and industry, which aims to help users discover the next interesting item. In this article, we propose a novel solution, namelygraph-augmented social translation model(GAST), which investigates the utility of dynamic social influence for the task of next-item recommendation. Specifically, we introduce a gated graph convolution module to better model long-term user preference. Furthermore, we design a cogating module to capture dynamic patterns at both sequential level and social level. In addition, a social-enhanced translation mechanism is devised to measure the intensity of user–item relationships. Extensive experiments under different recommendation scenarios demonstrate the rationality and effectiveness of our proposed GAST method over several state-of-the-art methods.

Next-item recommendation has been a hot research, which aims at predicting the next action by modeling users' behavior sequences. While previous efforts toward this task have been made in capturing complex item transition patterns, we argue that they still suffer from three limitations: 1) they have difficulty in explicitly capturing the impact of inherent order of item transition patterns; 2) only a simple and crude embedding is insufficient to yield satisfactory long-term users' representations from limited training sequences; and 3) they are incapable of dynamically integrating long-term and short-term user interest modeling. In this work, we propose a novel solution named graph-augmented capsule network (GCRec), which exploits sequential user behaviors in a more fine-grained manner. Specifically, we employ a linear graph convolution module to learn informative long-term representations of users. Furthermore, we devise a user-specific capsule module and a position-aware gating module, which are sensitive to the relative sequential order of the recently interacted items, to capture sequential patterns at union-level and point-level. To aggregate the long-term and short-term user interests as a representative vector, we design a dual-gating mechanism, which could decide the contribution ratio of each module given different contextual information. Through extensive experiments on four benchmarks, we validate the rationality and effectiveness of GCRec on the next-item recommendation task.

Generative adversarial nets (GANs) have enjoyed considerable success in computer vision and attracted much attention from recommender systems. However, due to the discrete nature of items, it is infeasible to graft GANs directly onto recommendation models. Although several methods have taken steps forward, their training processes are slow-convergent, time-consuming, or even unstable. This article proposes a novel framework named attentive adversarial collaborative filtering (AACF) and an efficient training strategy to improve GANs in recommender systems. There are two distinct novelties over previous work. First, AACF is a differentiable generative adversarial framework that introduces an attention mechanism and “virtual items” to bridge the gap between the generator and the discriminator. Owing to the intrinsic differentiability, AACF can be stably optimized with gradient descent methods. Second, the efficient training strategy substantially reduces computational complexity. It is capable of efficiently training and scaling up the AACF model to large datasets. Extensive experiments on various datasets demonstrate the effectiveness, fast convergence, stability, and scalability of AACF. Since our ideas are general in nature, they will open a path to stably and efficiently train GANs in the research areas with discrete data. The implementation code is available athttps://github.com/zhongchuansun/AACF.

A sequential recommendation has become a hot research topic, which seeks to predict the next interesting item for each user based on his action sequence. While previous methods have made many efforts to capture the dynamics of sequential patterns, we contend that they still suffer from two inherent limitations: 1) they fail to model item transition patterns in an efficient and time-sensitive manner and 2) they are unaware of the importance of dynamically capturing social influence, resulting in suboptimal performance. We introduce a new concept dubbed socio-sequential recommendation, where the challenge mainly lies in dynamically modeling social influences and capturing item-to-item transition patterns in a time-sensitive manner. In light of this, we contribute a novel solution named GCARec (short for graph-augmented co-attention model), which takes into account the joint effect of dynamic sequential patterns and dynamic social influences. GCARec decomposes socio-sequential recommendation workflow into two steps. First, we adopt a light graph embedding module to model long-term user preference. Then, we propose a time-sensitive attention mechanism and a social-aware attention mechanism to capture dynamic patterns at sequential-level and social-level, respectively. Extensive experiments have been conducted on eight real-world datasets from different scenarios, demonstrating the superiority of GCARec against several state-of-the-art methods. The codes and datasets have been released at:https://github.com/wubinzzu/GCARec.

In the era of Internet of Things (IoT), intelligent recommendation is playing an important role in our daily life. How to provide personalized information to users is the core concern of Internet content service providers. To improve the recommendation quality, it is a hot topic to go beyond merely user–item interaction records and take social relations into account in IoT. Recently, emerged graph neural networks (GNNs) shine a light on simulating the recursive social diffusion process, to refine user embedding learning. Nevertheless, two key issues have not been well studied in previous studies: 1) they usually model user preference and social influence within a same semantic space and fail to simultaneously inject high-order connectivity information reflected in both user–item interaction graph and user–user social graph and 2) they typically rely on negative sampling to optimize a recommendation model, which makes them highly sensitive to the design of the sampler and hardly makes full use of GPU’s computing ability. In light of this, we propose a novel framework for item recommendation, namely, an efficient adaptive graph convolutional network (EAGCN). Specifically, we introduce a space-adaptive graph convolutional module, which could jointly explore the propagation process of user interest and social influence. Furthermore, a user-specific gating mechanism is designed to aggregate user representations from both spaces. To make EAGCN practical in social IoT, we devise a fast nonsampling leaner to optimize EAGCN’s parameters with better leveraging matrix computing of GPU. Extensive experiments under four scenarios show that our solution consistently and significantly outperforms strong baseline methods in both model effectiveness and training efficiency.

An effective recommender system can significantly help customers to find desired products and assist business owners to earn more income. Nevertheless, the decision-making process of users is highly complex, not only dependent on the personality and preference of a user, but also complicated by the characteristics of a specific product. For example, for products of different domains (e.g., clothing versus office products), the product aspects that affect a user’s decision are very different. As such, traditional collaborative filtering methods that model only user-item interaction data would deliver unsatisfactory recommendation results. In this work, we focus on fine-grained modeling of product characteristics to improve recommendation quality. Specifically, we first divide a product’s characteristics into visual and functional aspects—i.e., thevisual appearanceandfunctionalityof the product. One insight is that, the visual characteristic is very important for products of visually-aware domain (e.g., clothing), while the functional characteristic plays a more crucial role for visually non-aware domain (e.g., office products). We then contribute a novel probabilistic model, namedVisual and Functional Probabilistic Matrix Factorization(VFPMF), to unify the two factors to estimate user preferences on products. Nevertheless, such an expressive model poses efficiency challenge in parameter learning from implicit feedback. To address the technical challenge, we devise a computationally efficient learning algorithm based on alternating least squares. Furthermore, we provide an online updating procedure of the algorithm, shedding some light on how to adapt our method to real-world recommendation scenario where data continuously streams in. Extensive experiments on four real-word datasets demonstrate the effectiveness of our method with both offline and online protocols.

Predicting what items a user will consume in the next time (i.e., next-item recommendation) is a crucial task for recommender systems. While the factorization method is a popular choice in recommendation, several recent efforts have shown that the inner product does not satisfy the triangle inequality, which may hurt the model's generalization ability. TransRec is a promising method to overcome this issue, which learns a distance metric to predict the strength of user-item interactions. Nevertheless, such method only uses the latest consumed item to model a user's short-term preference, which is insufficient for modeling fidelity. In this article, we propose a simple yet effective method named attentive translation model, to explicitly exploit high-order sequential information for next-item recommendation. Specifically, we construct a user-specific translation vector by accounting for multiple recent items, which encode more information about a user's short-term preference than the latest item. To aggregate multiple items into one representation, we devise a position-aware attention mechanism, learning different weights on items at different orders in a personalized way. Extensive experiments on four real-world datasets show that our method significantly outperforms several state-of-the-art methods.

Unlike all prior work, in this article, we investigate the notion of “unraveling metric vector spaces,” i.e., deriving meaning and low-rank structure from distance or metric space. Our new model bridges two commonly adopted paradigms for recommendations-metric learning approaches and factorization-based models, distinguishing itself accordingly. More concretely, we show that factorizing a metric vector space can be surprisingly efficacious. All in all, our proposed method, factorized metric learning, is highly effective for two classic recommendation tasks, possessing the potential of displacing many popular choices as an extremely strong baseline. We have done experiments on a number of real-world datasets, which show that our model performs better than recent state of the art largely on the rating prediction and item ranking tasks.

Deep learning based recommender systems have been extensively explored in recent years. However, the large number of models proposed each year poses a big challenge for both researchers and practitioners in reproducing the results for further comparisons. Although a portion of papers provides source code, they adopted different programming languages or different deep learning packages, which also raises the bar in grasping the ideas. To alleviate this problem, we released the open source project: \textbf{DeepRec}. In this toolkit, we have implemented a number of deep learning based recommendation algorithms using Python and the widely used deep learning package - Tensorflow. Three major recommendation scenarios: rating prediction, top-N recommendation (item ranking) and sequential recommendation, were considered. Meanwhile, DeepRec maintains good modularity and extensibility to easily incorporate new models into the framework. It is distributed under the terms of the GNU General Public License. The source code is available at github: https://github.com/cheungdaven/DeepRec

The rapid growth of Internet services and mobile devices provides an excellent opportunity to satisfy the strong demand for the personalized item or product recommendation. However, with the tremendous increase of users and items, personalized recommender systems still face several challenging problems: (1) the hardness of exploiting sparse implicit feedback; (2) the difficulty of combining heterogeneous data. To cope with these challenges, we propose a gated attentive-autoencoder (GATE) model, which is capable of learning fused hidden representations of items' contents and binary ratings, through a neural gating structure. Based on the fused representations, our model exploits neighboring relations between items to help infer users' preferences. In particular, a word-level and a neighbor-level attention module are integrated with the autoencoder. The word-level attention learns the item hidden representations from items' word sequences, while favoring informative words by assigning larger attention weights. The neighbor-level attention learns the hidden representation of an item's neighborhood by considering its neighbors in a weighted manner. We extensively evaluate our model with several state-of-the-art methods and different validation metrics on four real-world datasets. The experimental results not only demonstrate the effectiveness of our model on top-N recommendation but also provide interpretable results attributed to the attention modules.