Session-based recommendation (SBR) aims to provide users with satisfactory suggestions via modeling preferences based on short-term, anonymous user-item interaction sequences. Traditional single interest learning methods struggle to align with the diverse nature of preferences. Recent advances resolved this bottleneck by learning multiple interest embeddings for each session. However, due to the pre-defining scheme of interest quantity (e.g. the number of interests), these approaches are deficient in adaptive ability towards distinctive preference patterns across different users. Moreover, these methods rely solely on the current session and ignore useful information from related ones. The short-term property of sessions would magnify the insufficient representation issue. To address these limitations, we propose a Neural Process-based Multi-interest learning framework for Session-based Recommendation, namely NP-MiSR. To be specific, our method enables adaptive multi-interest representation learning through two complementary mechanisms: 1) Neural Process-based Intra-session interest modeling: We employ Neural Processes to model the distribution of interests within a session, where the fixed interest configurations are no longer needed. 2) Cross-session context fusion: We extract interest distributions of similar sessions as contextual priors to refine the current session’s interest representation. Extensive experiments on three datasets demonstrate that our method consistently outperforms state-of-the-art SBR approaches with an average improvement of 38.8%. Moreover, the few-shot learning task reveals that NP-MiSR achieves a surprisingly favorable efficiency v.s. performance trade-off where utilizing only 10% of the training data attains 95% of the recommendation performance.

Sparse Urban CrowdSensing (Sparse UCS) is a practical paradigm for completing full sensing maps from limited observations. However, existing methods typically rely on a time-discrete assumption, where data is considered static within fixed intervals. This simplification introduces significant errors as real-world data changes continuously. To address this, we propose a framework for time-continuous data completion. Our approach, Time-Aware Mamba-based Deep Matrix Factorization (TIME-DMF), leverages the Mamba architecture as a powerful temporal encoder. Crucially, we enhance Mamba with a novel time-aware mechanism that explicitly incorporates the actual, often irregular, physical time intervals between observations into its state transitions. This allows our model to accurately capture true temporal dynamics and generate high-fidelity data for any queried moment in time through a query-generate mechanism. Extensive experiments on five diverse sensing tasks demonstrate that TIME-DMF significantly outperforms state-of-the-art methods, validating the superiority of the time-continuous paradigm for Sparse UCS.

Urban region embedding, which learns dense vector representations for urban zones, plays a foundational role in data-driven urban intelligence. These representations are critical for downstream applications like public safety management and infrastructure development, requiring nuanced understanding of urban functionality. A core challenge remains effective fusion of multi-view data (e.g., human mobility flows and static regional attributes) into unified zone representations. To this end, we propose MVJC, a Multi-view Joint Learning and Contrastive Learning framework, which employs: (1) Multi-view Joint Learning (MVJL) layer to model intra-view dependencies to extract view-specific features and (2) Multi-view Contrastive Learning (MVCL) layer to perform cross-region aggregation to derive consensus representations while capturing the regional complementarity. We further introduce a structure-aware contrastive loss that mitigates false negatives by aligning representations through region topology instead of instance identity. Extensive experiments on New York City datasets demonstrate MVJC’s superiority: it reduces crime prediction MAE by 9.1% (vs. 66.9 baseline) and improves land use clustering F-measure by 55.6% (vs. 0.45 baseline) over state-of-the-art method, which is attributed to MVJC’s synergy of joint and contrastive learning, yielding representations that are simultaneously predictive and semantically discriminative.

Cross-Domain Recommendation (CDR) transfers user preferences from a source domain to alleviate data sparsity in a target domain. While disentangling representations into domain-specific and shared components is a common method, existing methods overlook user preference heterogeneity and item appeal heterogeneity. To this end, we propose DPGCDR, a Dual-Perspective Group-aware CDR method that learns symmetric group-aware representations from both user and item. Conceptually, DPGCDR dynamically clusters users into groups and items into themes, then symmetrically disentangles user preferences into group-specific and cross-group shared components, and item attributes into theme-specific and cross-theme shared components. We propose a two-stage training scheme: 1) an initial warm-up stage learns preliminary representations to dynamically cluster users and items into group and theme structures which generalize cross-domain scenarios into multi-group disentanglement analogous to multi-domain settings; 2) a fusion-based aggregation stage integrates these group/theme-specific components into unified global representations. Additionally, an information-theoretic alignment regularizer further ensures consistency and discriminability between global shared and group/theme-specific representations, facilitating effective knowledge transfer by explicitly modeling and preserving the inherent multi-group structure within cross-domain interactions. Extensive experiments show DPGCDR achieves state-of-the-art performance, with significant gains of up to 25% in HR@10 over baselines on datasets with heterogeneous interaction structures. Further analyses confirm our dynamic clustering mechanism effectively adapts to underlying data patterns, enabling fine-grained cross-domain knowledge transfer.

Abstract Data quality and budget are two major concerns in large-scale urban Mobile Crowdsensing (MCS) technologies. Traditional MCS research primarily measures data quality based on sensing coverage, without fully considering the importance of the data for downstream tasks. As a result, in Sparse Mobile Crowdsensing (SMCS), existing studies often focus on selecting the subregions most valuable for data inference, overlooking the ultimate goal of data collection, which is to support subsequent decision-making. With the rise of Embodied AI, a core challenge is how to actively collect key information that is most helpful for decision-making under conditions of sparse data and high costs. For example, in urban air quality monitoring, insufficient sensor deployment may cause critical polluted regions to go unobserved, undermining public health decisions. Similarly, sparse traffic data can lead to errors in autonomous driving systems, such as flawed route planning or hazard detection failures. As a feasible data collection paradigm for Embodied AI, existing SMCS subregion selection methods often ignore the relevance of data to tasks, thereby affecting decision-making in Embodied AI. To address this, we design a Sparse Mobile Crowdsensing active perception framework that selects the most valuable subregions for decision-making, considering the context of downstream tasks. Furthermore, existing SMCS subregion selection methods usually focus only on selecting the optimal subregion, whereas Embodied AI requires selecting a set of subregions. Choosing only the optimal subregion may overlook information overlap between subregions, leading to wasted data collection costs and reducing the perception efficiency of Embodied AI. This paper proposes an active acquisition strategy that takes into account parameter uncertainty and probabilistic margins, enabling the selection of an optimal set of subregions. Since this is an NP-hard problem, we approximate the proposed strategy using a greedy algorithm and provide performance guarantees for this approximation through theoretical proofs. Finally, we conduct experiments on three real-world datasets to validate the effectiveness of our proposed method. Experimental results show that when the data missing rate exceeds 60%, MBBALD starts to outperform other algorithms. On the traffic flow dataset, it achieves over 4% higher accuracy than the second-best algorithm at a 50% missing rate. Its advantage becomes more evident as the number of selected points increases, surpassing the second-best method by over 3% with more selected points.

Conventional multi-modal sequential recommenders usually employ sequence models (e.g., SASRec and GRU4Rec) as the recommender framework for sequential dependency modeling and multi-modal information as add-on knowledge for fine-grained preference learning. However, the existing methods ignore the time interval information in the interaction sequences, which reflects the user’s preference transition. Consequently, they acquire biased preference representations, leading to suboptimal performance. Along these lines, we concentrate on incorporating the time interval into the multi-modal sequential recommendation and investigating the internal influences across multiple modalities. Firstly, we treat the time interval as an independent modality and exploit a Time Interval Encoder (TIE) to quantify the time interval in the sequences. Secondly, we consider the heterogeneity between multiple modalities and design a two-stage fusion strategy. The first stage injects time intervals into each modality (ID, image, and text) and the second stage aggregates the user preferences from each modality to get the user’s sequence preferences. To this end, we build a model-agnostic framework for the multi-modal sequential recommendation, namely the Time-interval-aware Multi-Modal Sequential Recommender (TMMSRec) . The empirical validations on four real-world datasets prove the effectiveness of our method, where the maximum performance improvement against several state-of-the-art baselines achieves up to 16.05%. Our code is available at https://github.com/wangpp0602/TMMSRec .

Multi-interest recommendation constantly aspires to an oracle individual preference modeling approach, that satisfies the diverse and dynamic properties. Fueled by the deep learning technology, existing neural network (NN)-based recommender systems employ single-point or multi-point interest representation strategy to realize preference modeling,and boost the recommendation performance with a remarkable margin. However, as parameterized approximate functions, NN-based methods remain deficiencies with respect to the adaptability towards distinctive preference patterns cross different users and the calibration over the individual current intent. In this paper, we revisit multi-interest recommendation with the lens of stochastic process and Bayesian inference. Specifically, we propose to learn a distribution over functions to depict the individual diverse preferences rather than a unified function to approximate preference. Subsequently, the recommendation is encouraged with the uncertainty estimation which conforms to the dynamic shifting intent. Along these lines, we establish the connection between multi-interest recommendation and neural processes by proposing NP-Rec, which realizes the flexible multiple interests modeling and uncertainty estimation, simultaneously. Empirical study on 4 real world datasets demonstrates that our NP-Rec attains superior recommendation performances to several state-of-the-art baselines, where the average improvement achieves up to 13.94%.

Autonomous underwater vehicle (AUV) is crucial for marine applications such as ocean data collection, pollution monitoring, and navigation. However, their limited energy resources constrain their operational duration, posing a significant challenge for long-term operations. Due to the complex and unpredictable nature of the underwater environment, AUVs allocate energy to their sensing systems to sense the surrounding environment and avoid obstacles. Existing methods focus on reducing energy consumption on AUV computing and movement, neglecting sensing energy consumption and few attempts have been made to balance the AUV energy and sensing ability with a flexible sensing system. Along these lines, we consider both AUV energy consumption and flexible sensing abilities, and propose a deep reinforcement learning-based method to Reduce Energy Consumption by AUV Sensing system (RECS). Specifically, we build an AUV sensing system in a 2-dimension space, with controllable 8-direction sensing abilities to collect the environment information dynamically. Then we divide the underwater environment into several areas and assign weights on the edges of areas based on the AUV planned path. Additionally, we dynamically switch the sensors in different directions and radii to sense the edges of the area where the AUV is located. The Artificial Potential Field (APF) method is employed to re-plan the AUV path to avoid obstacles and reach the target point effectively. Experimental results demonstrate that compared to full sensors on, our method reduces energy consumption by 53.48% and is capable of generalizing to varying environments and varying sensing system radii.

Session-based recommendation (SBR) is widely used in e-commerce and streaming services, with the task of performing real-time recommendations based on short-term anonymous user history data. Most existing SBR frameworks follow the pattern of learning a single representation for a specific session, which makes it difficult to capture potential multiple interests, thus preventing discriminative recommendations. Multi-Interest learning has emerged as an effective approach for addressing this issue on sequential data in recent years. However, the current Multi-Interest frameworks act terrible on session data because they may generate excessive interests. To address these issues, we proposed a model named Dynamic Multi-Interst Graph Neural Network (DMI-GNN) ,which introduces the Multi-Interest learning framework into SBR and refines it by proposing a multiple positional patterns (MPP) learning method and a Dynamic Multi-Interest (DMI) regularization.To be specific, the MPP learning layer ensures the model to obtain representations with different positional information for sessions.The DMI regularization, on the other hand, mitigates the influence of excessive interests. Experiments on three bench-mark datasets demonstrate that our methods achieve better performance on different metrics

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.

Human preference alignment (HPA) aims to ensure Large Language Models (LLMs) responding appropriately to meet human moral and ethical requirements. Existing methods, such as RLHF and DPO, rely heavily on high-quality human annotation, which restrict the efficiency of iterative online model refinement. To address the inefficiencies of human annotation acquisition, iterated online strategy advocates the use of fine-tuned LLMs to self-generate preference data. However, this approach is prone to distribution bias, because of differences between human and model annotations, as well as modeling errors between simulators and real-world contexts. To mitigate the impact of distribution bias, we adopt the principles of adversarial training, framing a zero-sum two-player game with a protagonist agent and an adversarial agent. With the adversarial agent challenging the alignment of protagonist agent, we continuously refine the protagonist’s performance. By utilizing min-max equilibrium and Nash equilibrium strategies, we propose Indirect Online Preference Optimization (IOPO) mechanism that enables the protagonist agent to converge without bias while maintaining linear computational complexity. Extensive experiments across three real-world datasets demonstrate that IOPO outperforms state-of-the-art alignment methods in both offline and online scenarios, evidenced by standard alignment metrics and human evaluations. This innovation reduces the time required for model iterations from months to one week, alleviates distribution shifts, and significantly cuts annotation costs.

Sequential point-of-interest (POI) recommendation aims to recommend the next POI for users in accordance with their historical check-in information. However, few attempts treat timestamps of check-ins as a core factor for sequence models, leading to insufficient insight into user behavior and subsequently suboptimal recommendations. To address these limitations, we propose to assign equal importance to both POIs and their timestamps, shifting the point of view to recommend the next POI and predict the corresponding timestamp. Along these lines, we present the Time-Aware POI Recommender with Timestamp Prediction (TAPT), a multi-task learning framework for explainable POI recommendations. Specifically, we begin by decoupling timestamps into multi-dimensional vectors and propose a timestamp encoding module to explicitly encode these vectors. Additionally, we design a specialized timestamp prediction module built on the traditional sequence-based POI recommender backbone, effectively learning the strong correlation between POIs and their corresponding timestamps through these two modules. We evaluated the proposed model with three real-world LBSN datasets and demonstrated that TAPT achieves comparable or superior performance in POI recommendation compared to the baseline backbone. Besides, TAPT can not only recommend the next POI, but predict the corresponding timestamp in the future.

Sequential models aim to predict future interactions based on users' historical interaction sequences. Traditional sequential methods primarily focus on capturing intra-historical sequence dependencies, overlooking the influence of unobserved confounders in recommendation scenarios. Recent studies incorporate time as additional information helps the model capture dynamic user preferences. However, time is just the external manifestation of the influence of confounders but not the actual cause of the dynamic of user preference. Additionally, improperly integrating time with item embeddings can obstruct the model's ability to capture sequence dependencies. To address these challenges, we first revisit the sequential recommendation problem from a causal perspective and incorporate confounders as a new task. We propose a new framework—Flow-based Time-aware Causal Structure for Sequential Recommendation (FCSRec)—explicitly incorporating unobserved confounders' influence in the recommendation process. Specifically, we use Normalizing Flows to learn the causal graph of confounders and incorporate time information as conditional info to capture confounders' time-sensitive representations. To balance the influence of confounders and sequence dependencies, we introduce a classifier-free training paradigm by randomly masking the influence of confounders during training to encourage the model to learn both sequence dependencies and confounders' influence equally. We validate FCSRec on manifold real-world datasets, and experimental results show that FCSRec outperforms several state-of-the-art methods in recommendation performance. Our code is available at Code-link.

In this paper, we focus on the often-overlooked issue of embedding collapse in existing diffusion-based sequential recommendation models and propose ADRec, an innovative framework designed to mitigate this problem. Diverging from previous diffusion-based methods, ADRec applies an independent noise process to each token and performs diffusion across the entire target sequence during training. ADRec captures token interdependency through auto-regression while modeling per-token distributions through token-level diffusion. This dual approach enables the model to effectively capture both sequence dynamics and item representations, overcoming the limitations of existing methods. To further mitigate embedding collapse, we propose a three-stage training strategy: (1) pre-training the embedding weights(2) aligning these weights with the ADRec backbone, and (3) fine-tuning the model. During inference, ADRec applies the denoising process only to the last token, ensuring that the meaningful patterns in historical interactions are preserved. Our comprehensive empirical evaluation across six datasets underscores the effectiveness of ADRec in enhancing both the accuracy and efficiency of diffusion-based sequential recommendation systems.

Positive-Unlabeled (PU) learning refers to a specific weakly-supervised learning paradigm that induces a binary classifier with a few positive labeled instances and massive unlabeled instances. To handle this task, the community has proposed dozens of PU learning methods with various techniques, demonstrating strong potential. In this paper, we conduct a comprehensive study to investigate the basic characteristics of current PU learning methods. We organize them into two fundamental families of PU learning, including *disambiguation-free empirical risks*, which approximate the expected risk of supervised learning, and *pseudo-labeling methods*, which estimate pseudo-labels for unlabeled instances. First, we make an empirical analysis on disambiguation-free empirical risks such as uPU, nnPU, and DistPU, and suggest a novel risk-consistent set-aware empirical risk from the perspective of aggregate supervision. Second, we make an empirical analysis of pseudo-labeling methods to evaluate the potential of pseudo-label estimation techniques and widely applied generic tricks in PU learning. Finally, based on those empirical findings, we propose a general framework of PU learning by integrating the set-aware empirical risk with pseudo-labeling. Compared with existing PU learning methods, the proposed framework can be a practical benchmark in PU learning.

In recommender systems, it is frequently presumed that missing ratings adhere to a missing at random (MAR) mechanism, implying the absence of ratings is independent of their potential values. However, this assumption fails to hold in real-world scenarios, where users are inclined to rate items they either strongly favor or disfavor, introducing a missing not at random (MNAR) scenario. To tackle this issue, prior researchers have utilized explicit MAR feedbacks to infer the propensities of unobserved, implicit MNAR feedbacks. Nonetheless, acquiring explicit MAR feedbacks is resource-intensive and time-consuming and may not reflect users’ true preferences. Furthermore, most methods have only been tested on synthetic or small-scale datasets, thus their applicability and effectiveness in real-world settings without MAR feedbacks remain unclear. Along these lines, we aim to predict MNAR ratings without MAR prior propensities by exploring the consistency between MAR and MNAR feedbacks and narrowing the gap between them. From the empirical study and preliminary experiment, we hypothesize thatuser preferencescan be treated as the common prior propensity for both MAR and MNAR generative processes. In this way, we extend this hypothesis to a more general MNAR scenario: user preferences learned from MNAR can partially substitute for the prior propensities derived from MAR feedbacks for MNAR recommendation tasks. To validate our hypothesis and approach, we develop a lightweight iterative probabilistic matrix factorization framework (lightIPMF) as a practical method of our methodology, utilizing user preferences extracted from MNAR, not MAR, to estimate MNAR feedbacks. Finally, the experimental results show that modeling user preferences can effectively improve MNAR feedback estimation without MAR feedback, and our proposed lightIPMF outperforms the state-of-the-art MNAR methods in predicting MNAR feedbacks.

Mobilecrowdsensing (MCS) is a powerful technique that enables a variety of urban tasks, including temperature monitoring, location-based services, and urban path recommendations. However, these tasks often face the challenge of sparse and incomplete sensing data, undermining their effectiveness and reliability.Sparsedatacompletion (SDC) methods have been developed to infer missing or unobserved data by leveraging spatio-temporal correlations to tackle this issue. This forms the core concept of thesparsemobilecrowdsensing problem (SMCS), which aims to improve the performance of downstream tasks through inferred data. Despite the potential benefits, most existing SMCS methods fail to consider the trade-off between the cost of SDC and the benefits for downstream tasks. These methods often treat SDC and downstream tasks as independent modules, resulting in suboptimal outcomes. In this paper, we investigate the impact of SDC on the SMCS paradigm, both qualitatively and quantitatively. We establish the upper bound of performance achievable when applying SDC in SMCS under different levels of sensing data sparsity. Based on these studies and findings, we propose a practical and flexible framework calledSDC-EVA,SensingDataCompletionEVAluation framework. This framework allows for applying different SDC methods in SMCS, considering factors such as computing complexity, storage space, and associated costs. Our proposed framework allows researchers to assess the necessity and feasibility of integrating SDC into SMCS systems before designing and deploying them in real-world scenarios. This assessment can be tailored to specific data sparsity and contextual information. To validate the effectiveness of our proposed evaluation framework, we conduct experiments in various real-world scenarios involving different combinations of SDC and downstream tasks. The results demonstrate the superiority of our framework in improving the performance of SMCS. By presenting these findings, we aim to contribute to developing SMCS techniques and provide valuable insights for researchers and practitioners.

Inferring user preferences from users’ historical feedback is a valuable problem in recommender systems. Conventional approaches often rely on the assumption that user preferences in the feedback data are equivalent to the real user preferences without additional noise, which simplifies the problem modeling. However, there are various confounders during user–item interactions, such as weather and even the recommendation system itself. Therefore, neglecting the influence of confounders will result in inaccurate user preferences and suboptimal performance of the model. Furthermore, the unobservability of confounders poses a challenge in further addressing the problem. Along these lines, we refine the problem and propose a more rational solution to mitigate the influence of unobserved confounders. Specifically, we consider the influence of unobserved confounders, disentangle them from user preferences in the latent space, and employ causal graphs to model their interdependencies without specific labels. By ingeniously combining local and global causal graphs, we capture the user-specific effects of confounders on user preferences. Finally, we propose our model based on Variational Autoencoders, named Causal Structure Aware Variational Autoencoders (CSA-VAE) and theoretically demonstrate the identifiability of the obtained causal graph. We conducted extensive experiments on one synthetic dataset and nine real-world datasets with different scales, including three unbiased datasets and six normal datasets, where the average performance boost against several state-of-the-art baselines achieves up to 9.55%, demonstrating the superiority of our model. Furthermore, users can control their recommendation list by manipulating the learned causal representations of confounders, generating potentially more diverse recommendation results. Our code is available at Code-link ( https://github.com/MICLab-Rec/CSA ).

Learning item representation is crucial for a myriad of on-line e-commerce applications. The nucleus of retail item representation learning is how to properly fuse the semantics within a single item, and the interactions across different items generated by user behaviors (e.g., co-click or co-view). Product semantics depict the intrinsic characteristics of the item, while the interactions describe the relationships between items from the perspective of human perception. Existing approaches either solely rely on a single type of information or loosely couple them together, leading to hindered representations. In this work, we propose a novel model named TESPA to reinforce semantic modeling and interaction modeling mutually. Specifically, collaborative filtering signals in the interaction graph are encoded into the language models through fine-grained topological pre-training, and the interaction graph is further enriched based on semantic similarities. After that, a novel multi-channel co-training paradigm is proposed to deeply fuse the semantics and interactions under a unified framework. In a nutshell, TESPA is capable of enjoying the merits of both sides to facilitate item representation learning. Experimental results of on-line and off-line evaluations demonstrate the superiority of our proposal.

A high-performance network deployment strategy supports fundamental network services, such as topology controls, protocol designs, and boundary detections in underwater wireless sensor networks (UWSNs). Existing deployment methods treat nodes within the communication range as connected. However, in addition to internode distance, packet errors and collisions are also significant factors for point-to-point connectivity. Furthermore, when allocating node locations, deployment strategies focus on maximizing coverage, ignoring the tradeoff between coverage and network performance (reliability, latency, and energy efficiency). To this end, an efficient deployment scheme with network performance modeling (EDNPM) is proposed, to provide reliable data transmission in a time-aware and energy-efficient way for UWSNs. Specifically, we first explore sensor locations’ impact on communication and network factors, to improve the point-to-point connectivity and network performance. A network performance evaluation model (NPEM) is established to quantify performance metrics for guiding network deployment. Based on NPEM, network deployment is formulated as a multiobjective optimization problem, and we propose a novel network connection-constraint particle swarm optimization (NCPSO) algorithm to solve this problem. Notably, EDNPM is a unified network deployment framework for various underwater applications. Extensive experiments demonstrate that EDNPM outperforms other deployment algorithms in terms of network performance, and robustness with different network settings.

The past flourishing years of sequential location-based services began with the introduction of the Self-Attention Network (SAN), which quickly superseded CNN or RNN as the state-of-the-art backbone. Recent works utilize modified attention mechanisms or neural network layers to process spatial-temporal factors to realize fine-grained individual behavior pattern modeling. However, we argue these methods can be further improved due to the significant increase in the model's parameter scale or computational burden. In this paper, we first exploit two lightweight approaches, Rotary Time Aware Position Encoder (RoTAPE) and multi-head Interval Aware Attention Block (IAAB), to impel SAN by efficiently and effectively capturing spatial-temporal intervals among the user's visited locations, which require neither extra parameters nor a high computational cost. On the one hand, RoTAPE encodes the day- and hour-level timestamps into sequence representation simultaneously via a sinusoidal encoding matrix, and the corresponding time intervals can be explicitly captured by SAN. Specifically, the multi-level temporal differences are mutually independent to reflect the periodical pattern and jointly complete to measure the absolute time interval. On the other hand, IAAB, point- wise injecting the historical spatial-temporal intervals into the attention map, can promote SAN attaching importance to the spatial relations under the constraints of time conditions. Then, we design a novel MLP-based module, Spatial-Temporal Relation Memory (STR Memory), implemented with fully connected linear layers and matrix transpose operations. STR Memory, endowing the interactions inside historical intervals along different directions, can convert the historical intervals into spatial-temporal relations in future trajectories for accurate predictions. To this end, we propose an end-to-end mobility trajectory prediction framework, namely STiSAN$^+$, employing RoTAPE, stacking multiple layers of IAAB-based encoder-decoder architecture, and coupling with STR Memory. We conducted numerous experiments on six public LBSN datasets to evaluate our proposed algorithm. From Next Location Recommendation to Multi-location Future Trajectory Prediction, our STiSAN$^+$gains average 15.05% and 18.35% improvements against several state-of-the-art sequential models, respectively. Ablation studies demonstrate the effectiveness of RoTAPE, IAAB, and STR Memory under our framework. Moreover, we separately validate the extensibility and interpretability of RoTAPE and IAAB through non-sampled metric evaluation and visualization.

Recommender Systems (RSs) typically face the cold-start problem and the filter-bubble problem when users suffer the familiar, repeated, and even predictable recommendations, making them bored and unsatisfied. The key to solving these issues is learning users' fine-grained preferences and recommending appealing and unexplored items deviating from users' historical items. However, existing models consider cold-start or filter bubble problems separately and ignore that they can reinforce mutually and damage the models' performance accuracy. To this end, we devise a novel serendipity-oriented recommender system (GenerativeSelf-constrainedSerendipitousRecommenderSystem,GS$^{2}$-RS) that generates users' fine-grained preferences to enhance the recommendation performance. Specifically, GS$^{2}$-RS extracts users' interest and satisfaction preferences and generates virtual but convincible neighbors' preferences from themselves with a twin Conditional Generative Adversarial Nets (not from real neighbors). Then we introduce the serendipity item, which is low-interest but high-satisfaction among candidate items. We use the serendipity item to improve the diversity of recommended items, which relieves the filter-bubble problem. Along with this line, a gated mechanism is applied to their fine-grained preferences (interests, satisfactions) to obtain their serendipity items. Finally, these serendipity items are inversely injected into the original user-item rating matrix and build a relatively dense matrix as the input for backbone RS models. Note that GS$^{2}$-RS tackles cold-start and filter-bubble problems in a unified framework without any additional side information and enriches the interpretability of recommendation models. We comprehensively validate GS$^{2}$-RS for solving cold-start and filter bubble problems on four real-world benchmark datasets. Extensive experiments illustrate GS$^{2}$-RS's superiority in accuracy, serendipity, and interpretability over state-of-the-art models. Also, we can plug our model into existing recommender systems as a preprocessing procedure to enhance their performance.

Medium Access Control (MAC) protocols are critical for scheduling resources to access multiple users without collisions in Underwater Acoustic Networks (UANs). Due to harsh marine environments and limited communication resources, UANs lack a standard MAC protocol to adapt to various scenarios. The specific UAN scenario suffers from how to analyze multiple basic MAC protocols’ performance boundaries and modify the most potential one. A practical solution is to evaluate MAC protocols’ performance by modeling data loss (collisions and packet errors) and service time. However, existing models provide inaccurate performance results, since they ignore the effects of unique UANs’ characteristics and MAC protocol diversity on data loss and service time. In this paper, we propose a MAC Performance Analysis Framework (MPAF) for UANs to consider both unique UANs’ characteristics and MAC protocols’ diversity. We design Successful Transmission Probability (STP) model and Packet Service Time (PST) model in MPAF to estimate nodal throughput, delay, and energy consumption. STP model analyzes data loss types of different MAC protocols by considering long propagation delay, half-duplex communication, and random backoff to achieve a superior STP result from a view of real underwater communication conditions. Based on STP model, we employ Markov chain to deduce the retransmission number in PST model. In this way, MPAF ensures effectiveness and applicability in real-ocean environments. Extensive simulation results show that MPAF can accurately evaluate different MAC protocols’ performance boundaries, select the most appropriate basic protocol, and provide modified suggestions for a specific UAN scenario.

Mobile CrowdSensing (MCS) is a promising sensing paradigm that leverages users’ mobile devices to collect and share data for various applications. A key challenge in MCS is task allocation, which aims to assign sensing tasks to suitable users efficiently and effectively. Existing task allocation approaches are mostly centralized, requiring users to disclose their private information and facing high computational complexity. Moreover, centralized approaches may not satisfy users’ preferences or incentives. To address these issues, we propose a novel distributed task allocation scheme based on route navigation systems. We consider two scenarios: time-tolerant tasks and time-sensitive tasks, and formulate them as potential games. We design distributed algorithms to achieve Nash equilibria while considering users’ individual preferences and the platform’s task allocation objectives. We also analyze the convergence and performance of our algorithm theoretically. In the time-sensitive task scenario, the problem becomes even more intricate due to temporal conflicts among tasks. We prove the task selection problem is NP-hard and propose a distributed task selection algorithm. In contrast to existing distributed approaches that require users to deviate from their regular routes, our method ensures task completion while minimizing disruption to users. Trace-based simulation results validate that the proposed algorithm attains a Nash equilibrium and offers a total user profit performance closely aligned with that of the optimal solution.

In this work, we present TriMLP as a foundational MLP-like architecture for the sequential recommendation, simultaneously achieving computational efficiency and promising performance. First, we empirically study the incompatibility between existing purely MLP-based models and sequential recommendation, that the inherent fully-connective structure endows historical user–item interactions (referred as tokens) with unrestricted communications and overlooks the essential chronological order in sequences. Then, we propose the MLP-based Triangular Mixer to establish ordered contact among tokens and excavate the primary sequential modeling capability under the standard auto-regressive training fashion. It contains (1) a global mixing layer that drops the lower-triangle neurons in MLP to block the anti-chronological connections from future tokens and (2) a local mixing layer that further disables specific upper-triangle neurons to split the sequence as multiple independent sessions. The mixer serially alternates these two layers to support fine-grained preferences modeling, where the global one focuses on the long-range dependency in the whole sequence, and the local one calls for the short-term patterns in sessions. Experimental results on 12 datasets of different scales from 4 benchmarks elucidate that TriMLP consistently attains favorable accuracy/efficiency tradeoff over all validated datasets, where the average performance boost against several state-of-the-art baselines achieves up to 14.88%, and the maximum reduction of inference time reaches 23.73%. The intriguing properties render TriMLP a strong contender to the well-established RNN-, CNN-, and Transformer-based sequential recommenders. Code is available at https://github.com/jiangyiheng1/TriMLP .

Data analysis usually suffers from the Missing Not At Random (MNAR) problem, where the cause of the value missing is not fully observed. Compared to the naive Missing Completely At Random (MCAR) problem, it is more in line with the realistic scenario whereas more complex and challenging. Existing statistical methods model the MNAR mechanism by different decomposition of the joint distribution of the complete data and the missing mask. But we empirically find that directly incorporating these statistical methods into deep generative models is sub-optimal. Specifically, it would neglect the confidence of the reconstructed mask during the MNAR imputation process, which leads to insufficient information extraction and less-guaranteed imputation quality. In this paper, we revisit the MNAR problem from a novel perspective that the complete data and missing mask are two modalities of incomplete data on an equal footing. Along with this line, we put forward a generative-model-specific joint probability decomposition method, conjunction model, to represent the distributions of two modalities in parallel and extract sufficient information from both complete data and missing mask. Taking a step further, we exploit a deep generative imputation model, namely GNR, to process the real-world missing mechanism in the latent space and concurrently impute the incomplete data and reconstruct the missing mask. The experimental results show that our GNR surpasses state-of-the-art MNAR baselines with significant margins (averagely improved from 9.9% to 18.8% in RMSE) and always gives a better mask reconstruction accuracy which makes the imputation more principle.

Urban prediction tasks that aim to model the complicated spatial and temporal patterns of urban indicators (such as weather, vehicle charging demand, etc.) for accurate prediction, have been increasingly important in constructing smart cities and accelerating the urbanization process in the modern era. However, most existing works of urban prediction have only concentrated on spatial and temporal correlations, but ignored the effect of distribution shift from spatial and temporal perspectives; this could largely hinder the performance of urban prediction tasks. In order to solve this problem, in this paper, we propose a Shift-Aware Urban Prediction (SAUP) framework to eliminate the inherent shift effect among spatial-temporal urban time series data. Specifically, SAUP starts with a Shift Elimination Module, built upon our proposed Spatial-Temporal Attention Flows (STAF) composed of invertible attentions and coupling layers of normalizing flows in order to transform the raw shifted data into a unified distribution to remove the spatiotemporal shift. After the shift effect is eliminated, the Correlation Processing Module of SAUP further captures the core correlations to learn spatiotemporal dependencies, in which topological correlations and geographic correlations are jointly learned by GCN and CNN based on pre-defined graphs and extracted POI information. In addition, SAUP includes a model-agnostic Forecasting Module, which can be employed as any forecasting architecture to accomplish the predictions. To recover the raw distribution information, the output of the Forecasting Module is further taken for the inverse transformation of the Shift Elimination Module to produce the final forecasts. We have conducted extensive experiments in the SAUP framework, coupled with six state-of-the-art spatiotemporal forecasting models on two real-world datasets. Experimental results have demonstrated the consistent improvements of SAUP over the baseline algorithms.

Points-of-interest (POIs) recommendation plays a vital role in location-based social networks (LBSNs) by introducing unexplored POIs to consumers and has drawn extensive attention from academia and industry. Existing POI recommender systems usually learn fixed latent vectors to represent both consumers and POIs from historical check-ins and make recommendations under the spatio-temporal constraints. However, we argue that the existing works still suffer from the challenges of explaining consumers’ complicated check-in actions. To this end, we first explore the interpretability of recommendations from the POI aspect, i.e., for a specific POI, its function usually changes over time, so representing a POI with a single fixed latent vector is not sufficient to describe the dynamic nature of POIs. Besides, check-in actions to a POI are also affected by the zone where it is located. In other words, the zone's embedding learned from POI distributions, road segments, and historical check-ins could be jointly utilized to enhance POI embeddings. Along this line, we propose aTime-zone-spacePOI embedding model (ToP), which integrates multi-knowledge graphs and topic model to introduce not only spatio-temporal effects but also sentiment constraints into POI embeddings for strengthening interpretability of recommendation. Specifically, ToP learns multiple latent vectors for a POI in a different period with spatial constraints via knowledge graph learning. To add sentiment constraints, ToP jointly combines these vectors with the zone's representations learned by topic models to make explainable recommendations. ToP considers the time, space, and sentiment of POI in a unified embedding framework, which benefits the POI recommendations. Extensive experiments on real-world Changchun city datasets demonstrate that ToP achieves state-of-the-art performance in terms of common metrics and provides more insights for consumers’ POI check-in actions.

Mobile Crowdsensing (MCS) is a promising paradigm that recruits users to cooperatively perform a sensing task. When recruiting users, existing works mainly focus on selecting a group of users with the best objective ability, e.g., the user's probability or frequency of covering the task locations. However, we argue that the task completion effect depends not only on the user's objective ability, but also on their subjective collaboration likelihood with each other. Furthermore, even though we can find a well-behaved group of users in the single-round scenario, while in the multi-round scenario without enough prior knowledge, we still face the problem of recruiting previously well-behaved user groups (exploitation) or recruiting uncertain user groups (exploration). Additionally, we consider that each user has a different cost, and the platform recruits users under a cost budget; thus, the problem becomes more challenging: users may report fake costs to gain more profits. To address these problems, assuming that the user's information is known, we first convert the single-round user recruitment problem into the min-cut problem and propose a graph theory based algorithm to find the approximate solution. Then, in the multi-round scenario where the user's information is estimated from the previous rounds, to balance the trade-off between exploration and exploitation, we propose the multi-round User Recruitment strategy under the budget constraint based on the combinatorial Multi-armed Bandit model (URMB), which is proven to achieve a tight regret bound. Next, we propose a graph-based payment strategy to achieve truthfulness and individual rationality of users. Finally, extensive experiments on three real-world datasets show that URMB always outperforms the state-of-th-art strategies.

The past flourishing years of sequential point-of-interest (POI) recommendation began with the introduction of Self-Attention Network (SAN), which quickly superseded CNN or RNN as the state-of-the-art backbone. To realize the fine-grained users' behavior patterns modeling, recent works utilize modified attention mechanisms or neural network layers to process spatial-temporal factors. However, due to the significant increase on either model's parameter scale or computational burden, we argue that these methods can be further improved. In this paper, we exploit two lightweight approaches, Time Aware Position Encoder (TAPE) and Interval Aware Attention Block (IAAB), to impel SAN by considering the spatial-temporal intervals among POIs separately, where requiring neither extra parameters nor high computational cost. On the one hand, TAPE, adjusting the positions in sequences based on the timestamps dynamically and generating positional representations with sinusoidal transformation, can enhance sequence representations to reflect both the absolute order and relative temporal proximity among all POIs. On the other hand, IAAB, point-wise adding the scaled spatial-temporal intervals to the attention map, can promote the attention mechanism attaching importance to the spatial relation among all POIs under the constraints of time conditions and providing more explainable recommendation. We integrate these two modules into SAN and propose a Spatial-Temporal Interval-Aware sequential POI recommender, namely STiSAN, as an end-to-end deployment. Experimental results based on three public LBSN datasets and one real-world city transportation dataset demonstrate STiSAN's superior performance (average 13.01% improvement against the strongest baseline). Moreover, we validate the extensibility and interpretability of TAPE and IAAB through metric evaluation and visualization separately.

While Mobile CrowdSensing (MCS) has become a popular paradigm that recruits mobile users to carry out various sensing tasks collaboratively, the performance of MCS is frequently degraded due to the limited spatiotemporal coverage in data collection. A possible way here is to incorporate sparse MCS with data inference, where unsensed data could be completed through prediction. However, the spatiotemporal data inference is usually "fractured" with poor performance, because of following challenges: 1) the sparsity of the sensed data, 2) the unpredictability of a spatiotemporal fracture and 3) the complex spatiotemporal relations. To resolve such fracture data issues, we elaborate a data generative model for achieving spatiotemporal fracture data inference in sparse MCS. Specifically, an algorithm named Generative High-Fidelity Matrix Completion (GHFMC) is proposed through combining traditional Deep Matrix Factorization (DMF) and Generative Adversarial Networks (GAN) for generating spatiotemporal fracture data. Along this line, GHFMC learns to extract the features of spatiotemporal data and further efficiently complete and predict the unsensed data by using Binary Cross Entropy (BCE) loss. Finally, we conduct experiments on three popular datasets. The experimental results show that our approach performs higher than the state-of-the-art (SOTA) baselines in both data inference accuracy and fidelity.

Medical image registration is a fundamental and critical task in medical image analysis. With the rapid development of deep learning , convolutional neural networks (CNNs) have dominated the medical image registration field. Due to the disadvantage of the local receptive field of CNNs, some recent registration methods have focused on using transformers for nonlocal registration. However, the standard transformer has a vast number of parameters and high computational complexity, which means that it can only be applied at the bottom of registration models . As a result, only coarse information is available at the lowest resolution, limiting the contribution of the transformer in these models. To address these challenges, we propose a convolution-based efficient multihead self-attention (CEMSA) block, which reduces the number of parameters of the traditional transformer and captures local spatial context information to reduce semantic ambiguity in the attention mechanism. Based on the proposed CEMSA, we present a novel symmetric transformer-based model (SymTrans). SymTrans employs the transformer blocks in the encoder and the decoder to model the long-range spatial cross-image relevance. We apply SymTrans to the displacement field and diffeomorphic registration. Experimental results show that our proposed method achieves state-of-the-art performance in image registration. Our code is publicly available at https://github.com/MingR-Ma/SymTrans .

With the boosting of neural networks, recommendation methods become significantly improved by their powerful ability of prediction and inference. Existing neural-network based recommender systems (NN-RSs) usually first employ matrix embedding (ME) as a pre-process to learn users’ and items’ representations (latent vectors), then input these representations to a specific modified neural network framework to make accurate Top-k recommendations. Obviously, the performance of ME has a significant effect on RS models. However, most NN-RSs focus on accuracy by building representations from the direct user-item interactions (e.g., user-item rating matrix), while ignoring the underlying relatedness between users and items (e.g., users who rate the same ratings for the same items should be embedded into similar representations), which is an ideological disadvantage. On the other hand, ME models directly employ inner products as a default loss function metric that cannot project users and items into a proper latent space, which is a methodological disadvantage. In this paper, we propose a supervised collaborative representation learning model - Magnetic Metric Learning (MML) - to map users and items into a unified latent vector space, enhancing the representation learning for NN-RSs. First, MML utilizes dual triplets to model not only the observed relationships between users and items, but also the underlying relationships between users as well as items to overcome the ideological disadvantage. Specifically, a modified metric-based dual loss function is proposed in MML to gather similar entities and disperse the dissimilar ones. With MML, we can easily compare all the relationships (user to user, item to item, user to item) according to the weighted metric, which overcomes the methodological disadvantage. We conduct extensive experiments on four real-world datasets with large item space. The results demonstrate that MML can learn a proper unified latent space for representations from the user-item matrix with high accuracy and effectiveness, and lead to a performance gain over the state-of-the-art RS models by an average of 17 percent.

In e-commerce, online retailers are usually suffering from professional malicious users (PMUs), who utilize negative reviews and low ratings to their consumed products on purpose to threaten the retailers for illegal profits. PMUs are difficult to be detected because they utilize masking strategies to disguise themselves as normal users. Specifically, there are three challenges for PMU detection: 1) professional malicious users do not conduct any abnormal or illegal interactions (they never concurrently leave too many negative reviews and low ratings at the same time), and they conduct masking strategies to disguise themselves. Therefore, conventional outlier detection methods are confused by their masking strategies. 2) the PMU detection model should take both ratings and reviews into consideration, which makes PMU detection a multi-modal problem. 3) there are no datasets with labels for professional malicious users in public, which makes PMU detection an unsupervised learning problem. To this end, we propose an unsupervised multi-modal learning model: MMD, which employs Metric learning for professional Malicious users Detection with both ratings and reviews. MMD first utilizes a modified RNN to project the informational review into a sentiment score, which jointly considers the ratings and reviews. Then professional malicious user profiling (MUP) is proposed to catch the sentiment gap between sentiment scores and ratings. MUP filters the users and builds a candidate PMU set. We apply a metric learning-based clustering to learn a proper metric matrix for PMU detection. Finally, we can utilize this metric and labeled users to detect PMUs. Specifically, we apply the attention mechanism in metric learning to improve the model’s performance. The extensive experiments in four datasets demonstrate that our proposed method can solve this unsupervised detection problem. Moreover, the performance of the state-of-the-art recommender models is enhanced by taking MMD as a preprocessing stage.

Identifying the dynamic functions of different urban zones enables a variety of smart city applications, such as intelligent urban planning, real-time traffic scheduling, and community precision management. Traditional urban function research using government administrative zoning systems is often conducted in a coarse resolution with fixed split, and ignore the reshaping of zones by city growth. To solve this problem, we propose a two-stage framework in order to represent the high-definition distribution of urban function across the city, by analyzing continuous human traces extracted from the dense, widespread, and full-time cellular data. At the representation stage, we embed the locations of base stations by modeling the user movements with staying and transfer events, along with the consideration of dynamic trip purposes in continuous human traces. At the annotation stage, we first divide the city into the finest unit zones and each covers at least one base station. By clustering the base stations, we further group the unit zones into functional zones. Last, we annotate functional zones based on the local point-of-interest (POI) information. In experiments, we evaluate the proposed high-definition function study in two tasks: (i) in-zone crowd flow prediction, and (ii) zone-enhanced POI recommendation. The results demonstrate the advantage of the proposed method with both the effectiveness of city split and the high-quality function annotation.

Points-of-interest (POIs) recommendation plays a vital role by introducing unexplored POIs to consumers and has drawn extensive attention from both academia and industry. Existing POI recommender systems usually learn latent vectors to represent both consumers and POIs from historical check-ins and make recommendations under the spatiotemporal constraints. However, we argue that the existing works still suffer from the challenges of explaining consumers complicated check-in actions. In this paper, we first explore the interpretability of recommendations from the POI aspect, i.e., for a specific POI, its function usually changes over time, so representing a POI with a single fixed latent vector is not sufficient to describe POIs dynamic function. Besides, check-in actions to a POI is also affected by the zone it belongs to. In other words, the zone's embedding learned from POI distributions, road segments, and historical check-ins could be jointly utilized to enhance the accuracy of POI recommendations. Along this line, we propose a Time-dependent Zone-enhanced POI embedding model (ToP), a recommender system that integrates knowledge graph and topic model to introduce the spatiotemporal effects into POI embeddings for strengthening interpretability of recommendation. Specifically, ToP learns multiple latent vectors for a POI in different time to capture its dynamic functions. Jointly combining these vectors with zones representations, ToP enhances the spatiotemporal interpretability of POI recommendations. With this hybrid architecture, some existing POI recommender systems can be treated as special cases of ToP. Extensive experiments on real-world Changchun city datasets demonstrate that ToP not only achieves state-of-the-art performance in terms of common metrics, but also provides more insights for consumers POI check-in actions.

Sparse spatiotemporal data completion is crucial in Mobile CrowdSensing for urban application scenarios. In fact, accurate urban data completion can enhance data expression, improve urban analysis, and ultimately guide city planning. However, it is a non-trivial task to consider outlier values caused by the special events (e.g., parking peak, traffic congestion, or festival parade) in spatiotemporal data completion because of the following challenges: 1) the rarity and unpredictability, 2) the inconsistency compared to normal values, and 3) the complex spatiotemporal relations. In spite of the considerable improvements, recent deep learning-based methods overlook the existence of outlier values, which results in misidentifying these values. To this end, focusing on spatiotemporal data, we propose a matrix completion method that takes outlier value effects into consideration. Specifically, an outlier value model is proposed by adding a memory network and modifying the loss function to traditional matrix completion. Along this line, we extract the features of outlier values and further efficiently complete and predict the unsensed data. Finally, we conduct both qualitative and quantitative experiments on three different datasets, and the results demonstrate that the performance of our method outperforms the state-of-the-art baselines.

Mobile Edge Computing (MEC) has been envisioned as a promising distributed computing paradigm, where mobile users offload their tasks to edge nodes to decrease the cost of energy and computation. However, most existing works only consider the congestion of wireless channels as the crucial factor influencing the strategy-making process, and ignore the impact of the offloading among edge nodes. In addition, centralized task offloading strategies result in heavy computation complexity in center nodes. Along this line, we take both the congestion of wireless channels and the offloading among multiple edge nodes into consideration to enrich users’ offloading strategies. To this end, we first formulate the offloading problem as a multi-user potential game, and then propose a distributed task offloading algorithm to reach an equilibrium state which can also protect individual privacy. Specifically, in the above task offloading algorithm, we propose two subalgorithms to select users for updating strategies: Parallel User Selection Algorithm (PUS) and Single User Selection Algorithm (SUS) in order to substantially accelerate the convergence. Extensive experiments on three real-world data sets validate that the proposed algorithm achieves a Nash equilibrium and effectively decreases the total user cost which is acceptable compared to the optimal solution.

Mobile Crowdsensing (MCS) is a new paradigm that recruits users to cooperatively perform a sensing task. When recruiting users, existing works mainly focus on selecting a group of users with the best objective ability, e.g., the user's probability or frequency of covering the task locations. However, we argue that, for the cooperative MCS task, the completion effect depends not only on the user's objective ability, but also on their subjective collaboration likelihood with each other. In other words, in each single round, we prefer to recruit users with not only a strong objective ability but also good collaboration likelihood. Moreover, even though we could find a well-behaved group of users in a single round, in the multi-round scenario without enough prior knowledge, we still face the problem of recruiting previously well-behaved user groups (exploitation) or recruiting unknown user groups (exploration). To address these problems, in this paper, we first convert the single-round user recruitment problem into the min-cut problem and propose a graph theory based algorithm to find the optimal group of users. Furthermore, in the multi-round scenario, to balance the trade-off between exploration and exploitation, we propose the multi-round User Recruitment strategy based on the combinatorial Multi-armed Bandit model (URMB) and prove that it can achieve a tight regret bound. Finally, extensive experiments on three real-world datasets validate that the users recruited by URMB result in a better task completion effect than the state-of-the-art strategy.

Recommender systems have been playing an important role in providing personalized information to users. However, there is always a trade-off between accuracy and novelty in recommender systems. Usually, many users are suffering from redundant or inaccurate recommendation results. To this end, in this article, we put efforts into exploring the hidden knowledge of observed ratings to alleviate this recommendation dilemma. Specifically, we utilize some basic concepts to define a concept, Serendipity , which is characterized by high-satisfaction and low-initial-interest. Based on this concept, we propose a two-phase recommendation problem which aims to strike a balance between accuracy and novelty achieved by serendipity prediction and personalized recommendation. Along this line, a Neural Serendipity Recommendation (NSR) method is first developed by combining Muti-Layer Percetron and Matrix Factorization for serendipity prediction. Then, a weighted candidate filtering method is designed for personalized recommendation. Finally, extensive experiments on real-world data demonstrate that NSR can achieve a superior serendipity by a 12% improvement in average while maintaining stable accuracy compared with state-of-the-art methods.

In the existing recommender systems, matrix factorization (MF) is widely applied to model user preferences and item features by mapping the user-item ratings into a low-dimension latent vector space. However, MF has ignored the individual diversity where the user's preference for different unrated items is usually different. A fixed representation of user preference factor extracted by MF cannot model the individual diversity well, which leads to a repeated and inaccurate recommendation. To this end, we propose a novel latent factor model called adaptive deep latent factor model (ADLFM), which learns the preference factor of users adaptively in accordance with the specific items under consideration. We propose a novel user representation method that is derived from their rated item descriptions instead of original user-item ratings. Based on this, we further propose a deep neural networks framework with an attention factor to learn the adaptive representations of users. Extensive experiments on Amazon data sets demonstrate that ADLFM outperforms the state-of-the-art baselines greatly. Also, further experiments show that the attention factor indeed makes a great contribution to our method.

In real-world recommendation scenarios, there are two common phenomena: 1) users only provide ratings but there is no review comment. As a result, the historical transaction data available for recommender system are usually unbalanced and sparse; 2) Users' opinions can be better grasped in their reviews than ratings. This indicates that there is always a bias between ratings and reviews. Therefore, it is important that users' ratings and reviews should be mutually reinforced to grasp the users' true opinions. To this end, in this paper, we develop an opinion mining model based on convolutional neural networks for enhancing recommendation (NeuO). Specifically, we exploit a two-step training neural networks, which utilize both reviews and ratings to grasp users' true opinions in unbalanced data. Moreover, we propose a Sentiment Classification scoring method (SC), which employs dual attention vectors to predict the users' sentiment scores of their reviews. A combination function is designed to use the results of SC and user-item rating matrix to catch the opinion bias. Finally, a Multilayer perceptron based Matrix Factorization (MMF) method is proposed to make recommendations with the enhanced user-item matrix. Extensive experiments on real-world data demonstrate that our approach can achieve a superior performance over state-of-the-art baselines on real-world datasets.

In this paper, we study how to address the sparsity, accuracy and serendipity issues of top-N recommendation with collaborative filtering (CF). Existing studies commonly use rated items (which form only a small section in a rating matrix) or import some additional information (e.g., details about the items and users) to improve the performance of CF. Unlike these methods, we propose a novel notion towards a huge amount of unrated items: serendipity item. By utilizing serendipity items, we propose concise satisfaction and interest injection (CSII), a method that can effectively find interesting, satisfying, and serendipitous items in unrated items. By preventing uninteresting and unsatisfying items to be recommended as top-N items, this concise-but-novel method improves accuracy and recommendation quality (especially serendipity) substantially. Meanwhile, it can address the sparsity and cold-start issues by enriching the rating matrix in CF without additional information. As our method tackles rating matrix before recommendation procedure, it can be applied to most existing CF methods, such as item-based CF, user-based CF and matrix factorization-based CF. Through comprehensive experiments using abundant real-world datasets with LensKit implementation, we successfully demonstrate that our solution improves the performance of existing CF methods consistently and universally. Moreover, comparing with baseline methods, CSII can extract uninteresting items more carefully and cautiously, avoiding potential items inferred by mistake.

Summary Learning from positive and unlabeled examples (PU learning) is a partially supervised classification that is frequently used in Web and text retrieval system. The merit of PU learning is that it can get good performance with less manual work. Motivated by transfer learning, this paper presents a novel method that transfers the ‘outdated data’ into the process of PU learning. We first propose a way to measure the strength of the features and select the strong features and the weak features according to the strength of the features. Then, we extract the reliable negative examples and the candidate negative examples using the strong and the weak features (Transfer‐1DNF). Finally, we construct a classifier called weighted voting iterative support vector machine (SVM) that is made up of several subclassifiers by applying SVM iteratively, and each subclassifier is assigned a weight in each iteration. We conduct the experiments on two datasets: 20 Newsgroups and Reuters‐21578, and compare our method with three baseline algorithms: positive example‐based learning, weighted voting classifier and SVM. The results show that our proposed method Transfer‐1DNF can extract more reliable negative examples with lower error rates, and our classifier outperforms the baseline algorithms. Copyright © 2016 John Wiley & Sons, Ltd.