Large Language Models (LLMs) have been widely adopted in ranking systems such as information retrieval (IR) systems and recommender systems (RSs). To alleviate the latency of auto-regressive decoding, some studies explore the single (first) token decoding for ranking approximation, but they suffer from severe degradation in tail positions. Although speculative decoding (SD) methods can be a remedy with verification at different positions, they face challenges in ranking systems due to their left-to-right decoding paradigm. Firstly, ranking systems require strict latency constraints, but verification rounds in SD methods remain agnostic; Secondly, SD methods usually discard listwise ranking knowledge about unaccepted items in previous rounds, hindering future multi-token prediction, especially when candidate tokens are the unaccepted items. In this paper, we propose a Reinforcement Speculative Decoding method for fast ranking inference of LLMs. To meet the ranking systems' latency requirement, we propose an up-to-down decoding paradigm that employs an agent to iteratively modify the ranking sequence under a constrained budget. Specifically, we design a ranking-tailored policy optimization, actively exploring optimal multi-round ranking modification policy verified by LLMs via reinforcement learning (RL). To better approximate the target LLM under the constrained budget, we trigger the agent fully utilizing the listwise ranking knowledge about all items verified by LLMs across different rounds in RL, enhancing the modification policy of the agent. More importantly, we demonstrate the theoretical robustness and advantages of our paradigm and implementation. Experiments on both IR and RS tasks show the effectiveness of our proposed method.

Large language models (LLMs) are increasingly applied to ranking tasks in retrieval and recommendation. Although reasoning prompting can enhance ranking utility, our preliminary exploration reveals that its benefits are inconsistent and come at a substantial computational cost, suggesting that when to reason is as crucial as how to reason. To address this issue, we propose a reasoning routing framework that employs a lightweight, plug-and-play router head to decide whether to use direct inference (Non-Think) or reasoning (Think) for each instance before generation. The router head relies solely on pre-generation signals: i) compact ranking-aware features (e.g., candidate dispersion) and ii) model-aware difficulty signals derived from a diagnostic checklist reflecting the model's estimated need for reasoning. By leveraging these features before generation, the router outputs a controllable token that determines whether to apply the Think mode. Furthermore, the router can adaptively select its operating policy along the validation Pareto frontier at deployment time, enabling dynamic allocation of computational resources toward instances most likely to benefit from Think under varying system constraints. Experiments on three public ranking datasets with different scales of open-source LLMs show consistent improvements in ranking utility with reduced token consumption (e.g., +6.3% NDCG@10 with –49.5% tokens on MovieLens with Qwen3-4B), demonstrating reasoning routing as a practical solution to the accuracy-efficiency trade-off.

Large Language Models (LLMs) have been widely adopted in ranking systems, specifically for reranking tasks. Despite the effectiveness, the auto-regressive decoding of LLMs leads to inference latency due to the memory-bandwidth-bound. To alleviate this bottleneck, prior studies have explored single token decoding as an approximation, but they suffer from performance degradation at the tail positions of ranking. In this paper, we propose a Single Forward Pass (SFP)-based method to pre-verify multiple rankings using tree attention, approximating auto-regressive decoding by relevant sub-rankings at each step. However, verifying all possible ranking permutations will lead to factorial-level token computation (N!), making it intractable within SFP. To this end, we first reduce item ranking permutations to combinations (2N), based on the empirical observation that the LLM's next-item generation is less sensitive to the exact ordering of preceding items. Furthermore, we divide the full ranking into K sub-rankings and aggregate their individual probabilities, which further decreases the verification space to 2⌈N/K⌉ • K << 2N. However, naïvely aggregating sub-ranking probabilities leads to inaccurate estimates in listwise ranking. To overcome this, we introduce a Möbius inversion model that explicitly decompose the individual contribution of subsets within a complete lattice, as verified by tree attention. Then, we learn their higher-order effects with a hierarchical self-attention model to reconstruct the full ranking probability. Experiments on both information retrieval and recommendation tasks show the effectiveness of our proposed method.

Expert-sharing patterns have emerged as promising paradigms for multi-task learning (MTL) in recommender systems, enabling efficient resource allocation and dynamic modeling of diverse tasks. In this paper, we observe that high-gating (leader) and low-gating (auxiliary) experts play distinct roles in MTL: leader experts dominate task-specific predictions, while auxiliary experts, despite their lower gating scores, often contain complementary knowledge that can enhance model performance. However, critical challenges persist: how to effectively identify and utilize the knowledge of the leader and auxiliary experts in a synergistic manner? To address this, we propose a novel Dynamic Experts Synergy (DES) mechanism that integrates Entropy-driven Experts Classification (EEC) and Multi-view Knowledge Recycle (MVKR). EEC dynamically partitions experts into leader and auxiliary groups by analyzing task-specific prediction and gating entropy, enabling adaptive allocation aligned with real-time task difficulty. MVKR effectively revisits knowledge from auxiliary experts through utility, diversity, and task-relatedness perspectives, ensuring comprehensive knowledge utilization. Extensive experiments on five datasets demonstrate the superiority of our DES against state-of-the-art methods.

Decentralized learning (DL) has proven to be effective for privacy-preserving next point-of-interest (POI) recommendation by sharing check-in information among users and collaboratively training on-device models. Existing works, however, simply assume that users tend to share check-ins with neighbors of short geographical distance or similar preferences yet ignore users’ actual willingness to share the information (WSI), causing potential privacy concerns. As such, we present a WSI-guided hierarchical DL framework for next POI recommendation (WHDL-Rec) to seek enhanced privacy protection with recommendation accuracy assured. In particular, WHDL-Rec first performs hierarchical data segregation to partition the private and public user data. It then accords to the server-client architecture, where the server exploits the public data to automatically learn users’ WSI w.r.t. check-ins and capture global user behavior patterns for recommendation accuracy maintenance; and the clients fuse the learned global patterns with the local private data for personalized on-device next POI recommendation, whereby WSI-guided collaborative learning is conducted with more secure check-in sharing. Extensive experiments on three real-world datasets demonstrate the efficacy of WHDL-Rec in delivering more accurate and privacy-preserved recommendations.

Combinatorial optimization (CO) is fundamental to several realworld applications, from logistics and scheduling to hardware design and resource allocation.Deep reinforcement learning (RL) has recently shown significant benefits in solving CO problems, reducing reliance on domain expertise and improving computational efficiency.However, the absence of a unified benchmarking framework leads to inconsistent evaluations, limits reproducibility, and increases engineering overhead, raising barriers to adoption for new researchers.To address these challenges, we introduce RL4CO, a unified and extensive benchmark with in-depth library coverage of 27 CO problem environments and 23 state-of-the-art baselines.Built on efficient software libraries and best practices in implementation, RL4CO features modularized implementation and flexible configurations of diverse environments, policy architectures, RL algorithms, and utilities with extensive documentation.RL4CO helps researchers build on existing successes while exploring and developing their own designs, facilitating the entire research process by decoupling science from heavy engineering.We finally provide extensive benchmark studies to inspire new insights and future work.RL4CO has already attracted numerous researchers in the community and is open-sourced at https://github.com/ai4co/rl4co 1 .

New-items play a crucial role in recommender systems (RSs) for delivering fresh and engaging user experiences. However, traditional methods struggle to effectively recommend new-items due to their short exposure time and limited interaction records, especially in dynamic recommender systems (DRSs) where new-items get continuously introduced and users' preferences evolve over time. This leads to significant unfairness towards new-items, which could accumulate over the successive model updates, ultimately compromising the stability of the entire system. Therefore, we propose FairAgent, a reinforcement learning (RL)-based new-item fairness enhancement framework specifically designed for DRSs. It leverages knowledge distillation to extract collaborative signals from traditional models, retaining strong recommendation capabilities for old-items. In addition, FairAgent introduces a novel reward mechanism for recommendation tailored to the characteristics of DRSs, which consists of three components: 1) a new-item exploration reward to promote the exposure of dynamically introduced new-items, 2) a fairness reward to adapt to users' personalized fairness requirements for new-items, and 3) an accuracy reward which leverages users' dynamic feedback to enhance recommendation accuracy. Extensive experiments on three public datasets and backbone models demonstrate the superior performance of FairAgent. The results present that FairAgent can effectively boost new-item exposure, achieve personalized new-item fairness, while maintaining high recommendation accuracy.

Social recommendations (SRs) aim to enhance preference modeling by integrating social networks. However, their effectiveness is mainly constrained by two factors: the noisy social connections that may not reflect shared interests, and the limited number of social connections for most users, which hampers the system's ability to fully leverage social influence. Therefore, it is essential to perform social network refinement by removing noisy connections and adding meaningful ones for robust SRs. Inspired by the denoising capability of generative diffusion models, we propose a Model-Agnostic Social Network Refinement framework with Diffusion Models for Robust Social Recommendation (ARD-SR). Specifically, in the forward process, we corrupt the social network by progressively adding position-specific Gaussian noise calibrated to the user preference similarity, better simulating how the social network responds to noise perturbations. The reverse process learns to denoise, guided by each user's neighborhood preferences from the SR backbone, generating a tailored social network aligned with each user's preference for establishing connections. For effective learning, we design a curriculum-based training mechanism that progressively introduces challenging samples characterized by high sparsity or high noise levels. Finally, ARD-SR and the SR backbone are alternately trained, ensuring a continuous mutual enhancement between the social network refinement and the backbone's user representation learning. To further enhance the quality of the refined social network, (1) we introduce a preference-guided flip operation during inference to improve the input quality; and (2) we modify social connections based on the exponential weighted moving average of ARD-SR's predictions across epochs to reduce fluctuations. Experiments on three datasets show that ARD-SR significantly improves SR performance across multiple SR backbones. The code is released at https://github.com/sunyc123r/ARD-SR.

Continual learning is a process that involves training learning agents to sequentially master a stream of tasks or classes without revisiting past data. The challenge lies in leveraging previously acquired knowledge to learn new tasks efficiently, while avoiding catastrophic forgetting. Existing methods primarily focus on single domains, restricting their applicability to specific problems. In this work, we introduce a novel approach called Cross-Domain Continual Learning (CDCL) that addresses the limitations of being limited to single supervised domains. Our method combines inter- and intra-task cross-attention mechanisms within a compact convolutional network. This integration enables the model to maintain alignment with features from previous tasks, thereby delaying the data drift that may occur between tasks, while performing unsupervised cross-domain (UDA) between related domains. By leveraging an intra-task-specific pseudo-labeling method, we ensure accurate input pairs for both labeled and unlabeled samples, enhancing the learning process. To validate our approach, we conduct extensive experiments on public UDA datasets, showcasing its positive performance on cross-domain continual learning challenges. Additionally, our work introduces incremental ideas that contribute to the advancement of this field. We make our code and models available to encourage further exploration and reproduction of our results: https://github.com/IvsucramlCDCL

Recently, much effort has been devoted to modeling users' multi-interests (aka multi-faceted preferences) based on their behaviors, aiming to accurately capture users' complex preferences. Existing methods attempt to model each interest of users through a distinct representation, but these multi-interest representations easily collapse into similar ones due to a lack of effective guidance. In this paper, we propose a generic multi-interest method for sequential recommendation, achieving disentangled representation learning of diverse interests technically and theoretically. To alleviate the collapse issue of multi-interests, we propose to conduct item partition guided by their likelihood of being co-purchased in a global view. It can encourage items in each group to focus on a discriminated interest, thus achieving effective disentangled learning of multi-interests. Specifically, we first prove the theoretical connection between item partition and spectral clustering, demonstrating its effectiveness in alleviating item-level and facet-level collapse issues that hinder existing disentangled methods. To efficiently optimize this problem, we then propose a Markov Random Field (MRF)-based method that samples small-scale sub-graphs from two separate MRFs, thus it can be approximated with a cross-entropy loss and optimized through contrastive learning. Finally, we perform multi-task learning to seamlessly align item partition learning with multi-interest modeling for more accurate recommendation. Experiments on three real-world datasets show that our method significantly outperforms state-of-the-art methods and can flexibly integrate with existing multi-interest models as a plugin to enhance their performances.

Social Recommendation (SR) typically exploits neighborhood influence in the social network to enhance user preference modeling. However, users' intricate social behaviors may introduce noisy social connections for user modeling and harm the models' robustness. Existing solutions to alleviate social noise either filter out the noisy connections or generate new potential social connections. Due to the absence of labels, the former approaches may retain uncertain connections for user preference modeling while the latter methods may introduce additional social noise. Through data analysis, we discover that (1) social noise likely comes from the connected users with low preference similarity; and (2) Opinion Leaders (OLs) play a pivotal role in influence dissemination, surpassing high-similarity neighbors, regardless of their preference similarity with trusting peers. Guided by these observations, we propose a novel Self-Supervised Denoising approach through Independent Cascade Graph Augmentation, for more robust SR. Specifically, we employ the independent cascade diffusion model to generate an augmented graph view, which traverses the social graph and activates the edges in sequence to simulate the cascading influence spread. To steer the augmentation towards a denoised social graph, we (1) introduce a hierarchical contrastive loss to prioritize the activation of OLs first, followed by high-similarity neighbors, while weakening the low-similarity neighbors; and (2) integrate an information bottleneck based contrastive loss, aiming to minimize mutual information between original and augmented graphs yet preserve sufficient information for improved SR. Experiments conducted on two public datasets demonstrate that our model outperforms the state-of-the-art while also exhibiting higher robustness to different extents of social noise.

Most existing denoising recommendation methods alleviate noisy implicit feedback (user behaviors) through mainly empirical studies. However, such studies may lack theoretical explainability and fail to model comprehensive noise patterns, which hinders the understanding and capturing of different noise patterns that affect users’ behaviors. Thus, we propose to capture comprehensive noise patterns through theoretical and empirical analysis for more effective denoising, where users’ behaviors are divided into willingness and action phases to disentangle independent noise patterns. Willingness refers to the user’s intent to interact with an item, which may not lead to actual interaction due to different factors such as misclicking. Action denotes the user’s actual interaction with an item. Our analysis unveils that (1) in the willingness phase, high uncertainty in the user’s willingness to interact with the item can lead to high expectation loss which aligns with the findings of existing denoising methods; and (2) in the action phase, higher user-specific inconsistency between willingness and action not only leads to more noise in the user’s overall behaviors but also makes it harder to distinguish between true and noisy behaviors. Inspired by these findings, we propose a Unified Denoising Training (UDT) method for recommendation. To alleviate uncertainty in the willingness phase, we lower the importance of the user-item interaction with high willingness uncertainty recognized by high loss. To ease the inconsistency in the action phase, we lower the importance for users with high user-specific inconsistency as it may lead to noisier behaviors. Then, we increase the importance gap between the clean and noisy behaviors for users with low user-specific inconsistency as their behaviors are more distinguishable. Extensive experiments on three real-world datasets show that our proposed UDT outperforms state-of-the-art denoising recommendation methods.

Recommender systems tend to excessively expose longer-standing items, resulting in significant unfairness to new items with little interaction records, despite they may possess potential to attract considerable amount of users. The existing fairness-based solutions do not specifically consider the exposure fairness of new items, for which a systematic definition also lacks, discouraging the promotion of new items or contents. In this work, we introduce a multi-degree new-item exposure fairness definition, which considers item entry-time, and also is configurable regarding different fairness requirements. We then propose a configurable new-item fairness-aware framework named CNIF, which employs two-stage training where fairness degrees are incorporated for guidance. Extensive experiments on multiple popular datasets and backbone models demonstrate that CNIF can effectively enhance fairness of the existing models regarding the exposure resources of new items (including the brand-new items with no interaction). Specifically, CNIF demonstrates a substantial advancement with a 65.59% improvement in fairness metric and a noteworthy 9.97% improvement in recommendation accuracy compared to backbone models on the KuaiRec dataset. In comparison to various fairness-based solutions, it stands out by achieving the best trade-off between fairness and recommendation accuracy, surpassing the best baseline by 14.20%.

Artificial neural networks, celebrated for their human-like cognitive learning abilities, often encounter the well-known catastrophic forgetting (CF) problem, where the neural networks lose the proficiency in previously acquired knowledge. Despite numerous efforts to mitigate CF, it remains the significant challenge particularly in complex changing environments. This challenge is even more pronounced in cross-domain adaptation following the continual learning (CL) setting, which is a more challenging and realistic scenario that is under-explored. To this end, this article proposes a cross-domain CL approach making possible to deploy a single model in such environments without additional labelling costs. Our approach, namely continual learning approach for many processes (CLAMP), integrates a class-aware adversarial domain adaptation strategy to align a source domain and a target domain. An assessor-guided learning process is put forward to navigate the learning process of a base model assigning a set of weights to every sample controlling the influence of every sample and the interactions of each loss function in such a way to balance the stability and plasticity dilemma thus preventing the CF problem. The first assessor focuses on the negative transfer problem rejecting irrelevant samples of the source domain while the second assessor prevents noisy pseudo labels of the target domain. Both assessors are trained in the meta-learning approach using random transformation techniques and similar samples of the source domain. Theoretical analysis and extensive numerical validations demonstrate that CLAMP significantly outperforms established baseline algorithms across all experiments by at least 10% margin.

A typical benchmark dataset for recommender system (RecSys) evaluation consists of user-item interactions generated on a platform within a time period. The interaction generation mechanism partially explains why a user interacts with (e.g., like, purchase, rate) an item, and the context of when a particular interaction happened. In this study, we conduct a meticulous analysis of the MovieLens dataset and explain the potential impact of using the dataset for evaluating recommendation algorithms. We make a few main findings from our analysis. First, there are significant differences in user interactions at the different stages when a user interacts with the MovieLens platform. The early interactions largely define the user portrait which affect the subsequent interactions. Second, user interactions are highly affected by the candidate movies that are recommended by the platform's internal recommendation algorithm(s). Third, changing the order of user interactions makes it more difficult for sequential algorithms to capture the progressive interaction process. We further discuss the discrepancy between the interaction generation mechanism that is employed by the MovieLens system and that of typical real-world recommendation scenarios. That is, the MovieLens dataset records \(\langle user-MovieLens\rangle\) interactions, but not \(\langle user-movie\rangle\) interactions. All research articles using the MovieLens dataset model the \(\langle user-MovieLens\rangle\) rather than the \(\langle user-movie\rangle\) interactions, making their results less generalizable to many practical recommendation scenarios in real-world settings. In summary, the MovieLens platform demonstrates an efficient and effective way of collecting user preferences to address cold-starts. However, models that achieve excellent recommendation accuracy on the MovieLens dataset may not demonstrate superior performance in practice , for at least two kinds of differences: (1) the differences in the contexts of user-item interaction generation, and (2) the differences in user knowledge about the item collections. While results on MovieLens can be useful as a reference, they should not be solely relied upon as the primary justification for the effectiveness of a recommendation system model.

Conversational recommender system (CRS) enhances the recommender system by acquiring the latest user preference through dialogues, where an agent needs to decide “whether to ask or recommend”, “which attributes to ask”, and “which items to recommend” in each round. To explore these questions, reinforcement learning is adopted in most CRS frameworks. However, existing studies somewhat ignore to consider the connection between the previous rounds and the current round of the conversation, which might lead to the lack of prior knowledge and inaccurate decisions. In this view, we propose to facilitate the connections between different rounds of conversations in a dialogue session through deep transformer-based multi-channel meta-reinforcement learning, so that the CRS agent can decide each action/decision based on previous states, actions, and their rewards. Besides, to better utilize a user’s historical preferences, we propose a more dynamic and personalized graph structure to support the conversation module and the recommendation module. Experiment results on five real-world datasets and an online evaluation with real users in an industrial environment validate the improvement of our method over the state-of-the-art approaches and the effectiveness of our designs.

Current study on next point-of-interest (POI) recommendation mainly explores user sequential transitions with the fine-grained individual-user POI check-in trajectories only, which suffers from the severe check-in data sparsity issue. In fact, coarse-grained signals (i.e., region- and global-level check-ins) in such sparse check-ins would also benefit to augment user preference learning. Specifically, our data analysis unveils that user movement exhibits noticeable patterns w.r.t. the regions of visited POIs. Meanwhile, the global all-user check-ins can help reflect sequential regularities shared by the crowd. We are, therefore, inspired to propose the MCMG: a Multi-Channel next POI recommendation framework with Multi-Granularity signals categorized from two orthogonal perspectives, i.e., fine-coarse grained check-ins at either POI/region level or local/global level. The MCMG is equipped with three modules, namely, global user behavior encoder, local multi-channel (i.e., region, category, and POI channels) encoder, and region-aware weighting strategy. Such design enables MCMG to be capable of capturing both fine- and coarse-grained sequential regularities as well as exploring the dynamic impact of multi-channel by differentiating the check-in patterns w.r.t. visited regions. Extensive experiments on four real-world datasets show that our MCMG significantly outperforms state-of-the-art next POI recommendation approaches.

As the popularity of graph data increases, there is a growing need to count the occurrences of subgraph patterns of interest, for a variety of applications. Many graphs are massive in scale and also fully dynamic (with insertions and deletions of edges), rendering exact computation of these counts to be infeasible. Common practice is, instead, to use a small set of edges as a sample to estimate the counts. Existing sampling algorithms for fully dynamic graphs sample the edges with uniform probability. In this paper, we show that we can do much better if we sample edges based on their individual properties. Specifically, we propose a weighted sampling algorithm called WSD for estimating the subgraph count in a fully dynamic graph stream, which samples the edges based on their weights that indicate their importance and reflect their properties. We determine the weights of edges in a data-driven fashion, using a novel method based on reinforcement learning. We conduct extensive experiments to verify that our technique can produce estimates with smaller errors while often running faster compared with existing algorithms.

Item consumption and social connection, as common user behaviors in many web applications, have been extensively studied. However, most current works separately perform either item consumption or social link prediction tasks, possibly with the help of the other as an auxiliary signal. Moreover, they merely consider the behaviors in a holistic manner yet neglect the multi-faceted motives behind them. For example, the intention of watching a movie could be killing time or watching it with friends; Likewise, one might connect with others due to friendships or colleagues. To fill this gap, we propose to Disentangle the multi-faceted Motives in each network (i.e., the user-item interaction network and social network) defined respectively by the two types of behaviors, for mutually-enhanced Joint Prediction (DMJP). Specifically, we first learn the disentangled user representations driven by motives of multi-facets in both networks. Thereafter, the mutual influence of the two networks is subtly discriminated at the facet-to-facet level. The fine-grained mutual influence is then exploited asymmetrically to help refine user representations in both networks, with the goal of achieving a mutually-enhanced joint item and social link prediction. Empirical studies on three public datasets showcase the superiority of DMJP over state-of-the-arts (SOTAs) on both tasks.

Interactive recommender systems have attracted increasingly research attentions from both academia and industry. This workshop is a half-day event, which provides a forum for researchers and practitioners to discuss recent research progress and novel research directions about interactive recommender systems. The program will include two keynotes and 6 to 8 research paper presentations. The objective of this workshop is to consolidate the recent technical progresses about interactive recommendation, which will be a promising research and development direction for future recommendation technologies. This workshop will attract the attention of researchers from both academia and industry. It aligns with WSDM's spirit of promoting the collaborations between academia and industry.

Opinion Maximization (OM) aims at determining a small set of influential individuals, spreading the expected opinions of an object (e.g., product or individual) to their neighbors through the social relationships and eventually producing the largest opinion spread. In previous studies, once the corresponding nodes are activated, their opinions usually keep unchanged, which fails to capture the real scenarios where the opinion of each node on the object can dynamically change over time. In this view, we propose a Dynamic Opinion Maximization Framework (DOMF) to settle the OM problem, which consists of two parts: dynamic opinion formation and adaptive seeding process. Specifically, we formulate the OM problem by maximizing rational opinions, and prove that: 1) the OM problem within a constant ratio is NP-hard, and 2) the objective function does not satisfy the monotonicity and submodularity properties anymore. To model the dynamic opinion issue, we propose adaptive cooperation model based on Q-learning theory, which is proved to be capable of eventually reaching convergence. Moreover, to dynamically generate the initial seed nodes, we design the Multi-stage Heuristic Algorithm (MHA). Experimental results demonstrate that each component of our model is effective, and the proposed approach improves the rational opinion spread.

Online lot sizing for perishable materials in an uncertain environment is a fundamental problem for inventory planning and has been studied for several decades. In this article, we study a novel setting of thelotsizing problem, consideringperishable materials,multiple suppliers,uncertain demands and lead time (LS-PMU), which captures the inventory planning task in real life better than existing lot sizing problems. We present theoretical results of the best possible competitive ratio an online algorithm can achieve for the LS-PMU problem. We then develop a reinforcement learning-based algorithm calledRL4LSto intelligently choose the supplier and decide the order quantity in each time period. We conduct extensive experiments on both real and synthetic datasets to verify thatRL4LSoutperforms existing algorithms in terms of effectiveness and efficiency, e.g.,RL4LSimproves the effectiveness by 44% and runs two orders of magnitude faster than the state-of-the-art algorithmIBFA.

Dispatching vehicle fleets to serve flights is a key task in airport ground handling (AGH). Due to the notable growth of flights, it is challenging to simultaneously schedule multiple types of operations (services) for a large number of flights, where each type of operation is performed by one specific vehicle fleet. To tackle this issue, we first represent the operation scheduling as a complex vehicle routing problem and formulate it as a mixed integer linear programming (MILP) model. Then given the graph representation of the MILP model, we propose a learning assisted large neighborhood search (LNS) method using data generated based on real scenarios, where we integrate imitation learning and graph convolutional network (GCN) to learn a destroy operator to automatically select variables, and employ an off-the-shelf solver as the repair operator to reoptimize the selected variables. Experimental results based on a real airport show that the proposed method allows for handling up to 200 flights with 10 types of operations simultaneously, and outperforms state-of-the-art methods. Moreover, the learned method performs consistently accompanying different solvers, and generalizes well on larger instances, verifying the versatility and scalability of our method.

Recommender models are hard to evaluate, particularly under offline setting. In this article, we provide a comprehensive and critical analysis of the data leakage issue in recommender system offline evaluation. Data leakage is caused by not observing global timeline in evaluating recommenders e.g., train/test data split does not follow global timeline. As a result, a model learns from the user-item interactions that are not expected to be available at the prediction time. We first show the temporal dynamics of user-item interactions along global timeline, then explain why data leakage exists for collaborative filtering models. Through carefully designed experiments, we show that all models indeed recommend future items that are not available at the time point of a test instance, as the result of data leakage. The experiments are conducted with four widely used baseline models—BPR, NeuMF, SASRec, and LightGCN, on four popular offline datasets—MovieLens-25M, Yelp, Amazon-music, and Amazon-electronic, adopting leave-last-one-out data split. 1 We further show that data leakage does impact models’ recommendation accuracy. Their relative performance orders thus become unpredictable with different amount of leaked future data in training. To evaluate recommendation systems in a realistic manner in offline setting, we propose a timeline scheme, which calls for a revisit of the recommendation model design.

Collaborative filtering (CF) is widely used to learn informative latent representations of users and items from observed interactions. Existing CF-based methods commonly adopt negative sampling to discriminate different items. That is, observed user-item pairs are treated as positive instances; unobserved pairs are considered as negative instances and are sampled under a defined distribution for training. Training with negative sampling on large datasets is computationally expensive. Further, negative items should be carefully sampled under the defined distribution, in order to avoid selecting an observed positive item in the training dataset. Unavoidably, some negative items sampled from the training dataset could be positive in the test set. Recently, self-supervised learning (SSL) , has emerged as a powerful tool to learn a model without negative samples. In this paper, we propose a self-supervised collaborative filtering framework (SelfCF) , that is specially designed for recommender scenario with implicit feedback. The proposed SelfCF framework simplifies Siamese networks and can be easily applied to existing deep-learning based CF models, which we refer to as backbone networks. The main idea of SelfCF is to augment the latent embeddings generated by backbone networks instead of the raw input of user/item ids. We propose and study three embedding perturbation techniques that can be applied to different types of backbone networks including both traditional CF models and graph-based models. The framework enables learning informative representations of users and items without negative samples, and is agnostic to the encapsulated backbones. We conduct experimental comparisons on four datasets, one self-supervised framework, and eight baselines to show that our framework may achieve even better recommendation accuracy than the encapsulated supervised counterpart with a 2×–4× faster training speed. The results also demonstrate that SelfCF can boost up the accuracy of a self-supervised framework BUIR by 17.79% on average and shows competitive performance with baselines.

Multi-task learning (MTL) has been widely utilized in various industrial scenarios, such as recommender systems and search engines. MTL can improve learning efficiency and prediction accuracy by exploiting commonalities and differences across tasks. However, MTL is sensitive to relationships among tasks and may have performance degradation in real-world applications, because existing neural-based MTL models often share the same network structures and original input features. To address this issue, we propose a novel multi-task learning model based on Prototype Feature Extraction (PFE) to balance task-specific objectives and inter-task relationships. PFE is a novel component to disentangle features for multiple tasks. To better extract features from original inputs before gating networks, we introduce a new concept, namely prototype feature center, to disentangle features for multiple tasks. The extracted prototype features fuse various features from different tasks to better learn inter-task relationships. PFE updates prototype feature centers and prototype features iteratively. Our model utilizes the learned prototype features and task-specific experts for MTL. We implement PFE on two public datasets. Empirical results show that PFE outperforms state-of-the-art MTL models by extracting prototype features. Furthermore, we deploy PFE in a real-world recommender system (one of the world’s top-tier short video sharing platforms) to showcase that PFE can be widely applied in industrial scenarios.

Most existing studies on next point-of-interest (POI) recommendation assume that users deliver certain check-ins over individual POIs. In reality, we typically obtain uncertain check-ins due to the presence of collective POIs, which are gathering places of multiple individual POIs (e.g., shopping malls). On one hand, such uncertain check-ins over collective POIs hinder more accurate next POI recommendation for users due to the transition vanishing issue; on the other hand, the presence of collective POIs poses the challenge for businesses to select which collective POIs to locate in due to complicated competition and cooperation relations between businesses. As such, these collective POIs bring an unprecedented opportunity and necessity on recommendation for both users and businesses. Therefore, we propose novel solutions of location service beneficial for users-businesses. For users, we propose the STSP equipped with category- and location-aware encoders, to deliver more accurate next POI prediction by fusing rich context features. Regarding businesses, we explore their competition and cooperation relations from check-in records, based on which we derive theliving environment(LE) of a business. Insight on site selection for businesses is provided by exploiting the LE, aiming to bring in more profits. Extensive empirical studies demonstrate the efficiency of our solutions.

The e-commerce era is witnessing rising new arrivals of items on e-commerce platforms every day. Identifying potential popular items accurately is of great importance in creating commercial value. Click-Through Rate (CTR) is a general indicator to evaluate item popularity. However, existing methods fail in new arrivals prediction because of sparse item features, missing item statistics and high time complexity of computing for all pairs of users and items. To tackle these challenges, we propose a novel Adversarial Two-tower Neural Network (ATNN) model for new arrivals CTR predictions by introducing an adversarial network to a two-tower network. We design a generator and a discriminator to better learn an item vector based on item profiles without item statistics. We also develop a strategy with an O(1) time complexity for a new item's popularity prediction by constructing a user group and utilizing its mean user vector in a time-efficient manner. We implement ATNN on a largescale real-world dataset from one of the world's largest ecommerce platforms, “Tmall.com”. Empirical results show that ATNN is strongly capable of learning item vectors from item profiles for e-commerce. Furthermore, by introducing multi-task learning technology, we extend ATNN to food delivery service. Experimental results on one popular food delivery platform, “Ele.me”, demonstrate that ATNN can recognize attractive and welcoming new restaurants that have higher Value per Page View (VpPV) and generate more Gross Merchandise Volume (GMV).

Recommender Systems (RSs) in real-world applications often deal with billions of user interactions daily. To capture the most recent trends effectively, it is common to update the model incrementally using only the newly arrived data. However, this may impede the model’s ability to retain long-term information due to the potential overfitting and forgetting issues. To address this problem, we propose a novel Adaptive Sequential Model Generation (ASMG) framework, which generates a better serving model from a sequence of historical models via a meta generator. For the design of the meta generator, we propose to employ Gated Recurrent Units (GRUs) to leverage its ability to capture the long-term dependencies. We further introduce some novel strategies to apply together with the GRU meta generator, which not only improve its computational efficiency but also enable more accurate sequential modeling. By instantiating the model-agnostic framework on a general deep learning-based RS model, we demonstrate that our method achieves state-of-the-art performance on three public datasets and one industrial dataset.

Bipartite matching between two sets of objects is widely applied in many applications such as crowdsourcing marketplaces, ride-hailing services and logistics.Depending on the applications, different objectives have been proposed, resulting in different matching problems.Among them, one that is recently proposed is online bottleneck matching with delays (OBM-D), where the objective is to optimize the maximum cost of matches and the cost of a match depends on when the match is formed (i.e., it is delay-aware).Existing solutions for OBM-D usually adopt a holding strategy, which holds the objects involved in a match available for a period so as to reduce the chance that a bad match is formed.Nevertheless, existing holding strategies are all based on humancrafted rules thus cannot adapt to the dynamics of how the objects arrive.In this paper, we propose an adaptive holding strategy which is based on reinforcement learning and develop a method called Adaptive-H on top of the new holding strategy.Besides, we prove theoretical results on how good a randomized algorithm could achieve for the OBM-D problem in terms of competitive ratio.We conduct extensive experiments on both real and synthetic datasets to verify that Adaptive-H outperforms existing algorithms in terms of both effectiveness and efficiency.

Large-scale online promotions, such as Double 11 and Black Friday, are of great value to e-commerce platforms nowadays. Traditional methods are not successful when we aim to maximize global Gross Merchandise Volume (GMV) in the promotion scenarios due to three limitations. The first is that the GMV of sellers varies significantly from daily scenarios to promotions. Second, these methods do not consider explosive demands in promotions, so that a consumer may fail to purchase some popular items due to sellers' limited capacities. Third, the traffic distribution over sellers presents divergence in different channels, thus rendering the performance of the traditional single-channel methods far from optimal in creating commercial values. To address these problems, we design a Multi-Channel Sellers Traffic Allocation (MCSTA) optimization model to obtain optimal page view (PV) distribution concerning global GMV. Then we propose a general constrained non-smooth convex optimization solution with a Multi-Objective Shortest Distance (MOSD) hyperparameter tuning method to solve MCSTA. This is the first work to systematically address this issue in the scenario of large-scale online promotions. The empirical results show that MCSTA achieves significant improvement of GMV by 1.1% based on A/B test during Alibaba's "Global Shopping Festival", one of the world's largest online sales events. Furthermore, we deploy MCSTA in other popular scenarios, including everyday promotion and video live stream service, to showcase that MCSTA can be widely applied in e-commerce and online entertainment services.

With tremendous amount of recommendation algorithms proposed every year, one critical issue has attracted a considerable amount of attention: there are no effective benchmarks for evaluation, which leads to two major concerns, i.e., unreproducible evaluation and unfair comparison. This paper aims to conduct rigorous (i.e., reproducible and fair) evaluation for implicit-feedback based top-N recommendation algorithms. We first systematically review 85 recommendation papers published at eight top-tier conferences (e.g., RecSys, SIGIR) to summarize important evaluation factors, e.g., data splitting and parameter tuning strategies, etc. Through a holistic empirical study, the impacts of different factors on recommendation performance are then analyzed in-depth. Following that, we create benchmarks with standardized procedures and provide the performance of seven well-tuned state-of-the-arts across six metrics on six widely-used datasets as a reference for later study. Additionally, we release a user-friendly Python toolkit, which differs from existing ones in addressing the broad scope of rigorous evaluation for recommendation. Overall, our work sheds light on the issues in recommendation evaluation and lays the foundation for further investigation. Our code and datasets are available at GitHub (https://github.com/AmazingDD/daisyRec).

Popularity is often included in experimental evaluation to provide areference performance for a recommendation task. To understand how popularity baseline is defined and evaluated, we sample 12 papers from top-tier conferences including KDD, WWW, SIGIR, and RecSys, and 6 open source toolkits. We note that the widely adoptedMostPop baseline simply ranks items based on the number of interactions in the training data. We argue that the current evaluation of popularity (i) does not reflect the popular items at the time when a user interacts with the system, and (ii) may recommend items released after a user's last interaction with the system. On the widely used MovieLens dataset, we show that the performance of popularity could be significantly improved by 70% or more, if we consider the popular itemsat the time point when a user interacts with the system. We further show that, on MovieLens dataset, the users having lower tendencies on movies tend to follow the crowd and rate more popular movies. Movie lovers who rate a large number of movies, rate movies based on their own preferences and interests. Through this study, we call for a re-visit of the popularity baseline in recommender system to better reflect its effectiveness.

Given a graph G and a vertex q ∊ G, the community search (CS) problem aims to efficiently find a subgraph of G whose vertices are closely related to q. Communities are prevalent in social and biological networks, and can be used in product advertisement and social event recommendation. In this paper, we study profiled community search (PCS), where CS is performed on a profiled graph. This is a graph in which each vertex has labels arranged in a hierarchical manner. Compared with existing CS approaches, PCS can sufficiently identify vertices with semantic commonalities and thus find more high-quality diverse communities. As a naive solution for PCS is highly expensive, we have developed a tree index, which facilitates efficient and online solutions for PCS.

In this paper, we propose MUSE-RNN, a multilayer self-evolving recurrent neural network model for real-time classification of streaming data. Unlike the existing approaches, MUSE-RNN offers special treatment towards capturing temporal aspects of data stream through its novel recurrent learning approach based on the teacher forcing policy. Novelties here are twofold. First, in contrast to the traditional RNN models, MUSE-RNN has intrinsic ability to self-adjust its capacity by growing and pruning hidden nodes as well as layers, to handle the ever-changing characteristics of data stream. Second, MUSERNN adopts a unique scoring-based layer adaptation mechanism, which makes it capable of recalling prior tasks, with minimum exploitation of network parameters. The performance of MUSERNN is evaluated in comparison with a number of state-of-theart techniques, using seven popular data streams and continual learning problems under prequential test-then-train protocol. Experimental results demonstrate the effectiveness of MUSERNN in stream classification scenario.

Given a graph $G$G and a vertex $q\in G$q∈G, the community search (CS) problem aims to efficiently find a subgraph of $G$G whose vertices are closely related to $q$q. Communities are prevalent in social and biological networks, and can be used in product advertisement and social event recommendation. In this paper, we study profiled community search (PCS), where CS is performed on a profiled graph. This is a graph in which each vertex has labels arranged in a hierarchical manner. Extensive experiments show that PCS can identify communities with themes that are common to their vertices, and is more effective than existing CS approaches. As a naive solution for PCS is highly expensive, we have also developed a tree index, which facilitates efficient and online solutions for PCS.

The vastly diverse and increasingly autonomous Internet of Things (IoT) devices stress trust management as a critical requirement of IoT. This paper addresses subjectivity as an important issue in trust management for IoT. Subjectivity means that the information provided by each autonomous IoT device, represented by an agent, is likely to have been influenced by the device's individual preference, which can be misleading in trust evaluation. In this paper, we seek to align the potentially subjective information with the information seeker's own subjectivity so that the acquired second-hand information is more useful and personalized. Accordingly, we propose a multiagent subjectivity alignment (MASA) mechanism, which models the subjectivity using a regression technique and exchanges the models among agents as the input to an alignment process. This mechanism substantially counteracts biases incurred by different agents and improves the accuracy of second-hand information fusion as demonstrated by our simulations. In addition, we also conduct experiments using a real-world dataset (MovieLens) which further validates the efficacy of MASA.

Knowledge graphs (KGs) have proven to be effective to improve recommendation. Existing methods mainly rely on hand-engineered features from KGs (e.g., meta paths), which requires domain knowledge. This paper presents RKGE, a KG embedding approach that automatically learns semantic representations of both entities and paths between entities for characterizing user preferences towards items. Specifically, RKGE employs a novel recurrent network architecture that contains a batch of recurrent networks to model the semantics of paths linking a same entity pair, which are seamlessly fused into recommendation. It further employs a pooling operator to discriminate the saliency of different paths in characterizing user preferences towards items. Extensive validation on real-world datasets shows the superiority of RKGE against state-of-the-art methods. Furthermore, we show that RKGE provides meaningful explanations for recommendation results.

Personalized recommendation for online service systems aims to predict potential demand by analysing user preference. User preference can be inferred from heterogeneous implicit feedback (i.e. various user actions) especially when explicit feedback (i.e. ratings) is not available. However, most methods either merely focus on homogeneous implicit feedback (i.e. target action), e.g., purchase in shopping websites and forward in Twitter, or dispose heterogeneous implicit feedback without the investigation of its speciality. In this paper, we adopt two typical actions in online service systems, i.e., view and like , as auxiliary feedback to enhance recommendation performance, whereby we propose a Bayesian personalized ranking method for heterogeneous implicit feedback (BPRH). Specifically, items are first classified into different types according to the actions they received. Then by analysing the co-occurrence of different types of actions, which is one of the fundamental speciality of heterogeneous implicit feedback systems, we quantify their correlations, based on which the difference of users’ preference among different types of items is investigated. An adaptive sampling strategy is also proposed to tackle the unbalanced correlation among different actions. Extensive experimentation on three real-world datasets demonstrates that our approach significantly outperforms state-of-the-art algorithms.

Arriving on time and total travel time are two important properties for vehicle routing. Existing route guidance approaches always consider them independently, because they may conflict with each other. In this article, we develop a semi-decentralized multiagent-based vehicle routing approach where vehicle agents follow the local route guidance by infrastructure agents at each intersection, and infrastructure agents perform the route guidance by solving a route assignment problem. It integrates the two properties by expressing them as two objective terms of the route assignment problem. Regarding arriving on time, it is formulated based on the probability tail model, which aims to maximize the probability of reaching destination before deadline. Regarding total travel time, it is formulated as a weighted quadratic term, which aims to minimize the expected travel time from the current location to the destination based on the potential route assignment. The weight for total travel time is designed to be comparatively large if the deadline is loose. Additionally, we improve the proposed approach in two aspects, including travel time prediction and computational efficiency. Experimental results on real road networks justify its ability to increase the average probability of arriving on time, reduce total travel time, and enhance the overall routing performance.

Capturing the temporal dynamics of user preferences over items is important for recommendation. Existing methods mainly assume that all time steps in user-item interaction history are equally relevant to recommendation, which however does not apply in real-world scenarios where user-item interactions can often happen accidentally. More importantly, they learn user and item dynamics separately, thus failing to capture their joint effects on user-item interactions. To better model user and item dynamics, we present the Interacting Attention-gated Recurrent Network (IARN) which adopts the attention model to measure the relevance of each time step. In particular, we propose a novel attention scheme to learn the attention scores of user and item history in an interacting way, thus to account for the dependencies between user and item dynamics in shaping user-item interactions. By doing so, IARN can selectively memorize different time steps of a user's history when predicting her preferences over different items. Our model can therefore provide meaningful interpretations for recommendation results, which could be further enhanced by auxiliary features. Extensive validation on real-world datasets shows that IARN consistently outperforms state-of-the-art methods.

Belief fusion consists of taking into account multiple sources of belief about a domain of interest. This paper describes cumulative and averaging multi-source belief fusion in the formalism of subjective logic, which represent generalisations of binary-source belief fusion operators previously described. The advantage of this approach is that we can model and analyse belief fusion situations involving an arbitrary number of sources.

Different belief sources often provide conflicting evidence, due to e.g. varying source reliability or deliberate deception. Source trust expresses the source reliability as seen by the analyst. In case of conflicting sources the analyst needs a strategy for managing and revising source trust. Intuitively, trust should be reduced for sources that produce advice which is in conflict with the ground truth, or in conflict with the advice from other highly trusted sources. The present paper uses the formalism of subjective logic to describe strategies for source trust revision according to this principle.

The "International Workshop on Recommender Systems for Citizens" (CitRec) is focused on a novel type of recommender systems both in terms of ownership and purpose: recommender systems run by citizens and serving society as a whole.

We address the collusive opinion fraud problem in online review portals, where groups of people work together to deliver deceptive reviews for manipulating the reputations of targeted items. Such collusive fraud is considered much harder to defend against, since the participants (or colluders) can evade detection by shaping their behaviors collectively so as not to appear suspicious. To alleviate this problem, countermeasures have been proposed that leverage the collective behaviors of colluders. The motivation stems from the observation that colluders typically act in a very synchronized way, as they are instructed by the same campaigns with common items to target and schedules to follow. However, the collective behaviors examined in existing solutions focus mostly on the external appearance of fraud campaigns, such as the campaign size and the size of the targeted item set. These signals may become ineffective once colluders have changed their behaviors collectively. Moreover, the detection algorithms used in existing approaches are designed to only make collusion inference on the input data; predictive models that can be deployed for detecting emerging fraud cannot be learned from the data. In this article, to complement existing studies on collusive opinion fraud characterization and detection, we explore more subtle behavioral trails in collusive fraud practice. In particular, a suite of homogeneity-based measures are proposed to capture the interrelationships among colluders within campaigns. Moreover, a novel statistical model is proposed to further characterize, recognize, and predict collusive fraud in online reviews. The proposed model is fully unsupervised and highly flexible to incorporate effective measures available for better modeling and prediction. Through experiments on two real-world datasets, we show that our method outperforms the state of the art in both characterization and detection abilities.

Existing feature-based recommendation methods incorporate auxiliary features about users and/or items to address data sparsity and cold start issues. They mainly consider features that are organized in a flat structure, where features are independent and in a same level. However, auxiliary features are often organized in rich knowledge structures (e.g. hierarchy) to describe their relationships. In this paper, we propose a novel matrix factorization framework with recursive regularization -- ReMF, which jointly models and learns the influence of hierarchically-organized features on user-item interactions, thus to improve recommendation accuracy. It also provides characterization of how different features in the hierarchy co-influence the modeling of user-item interactions. Empirical results on real-world data sets demonstrate that ReMF consistently outperforms state-of-the-art feature-based recommendation methods.

We propose TrustSVD, a trust-based matrix factorization technique for recommendations. TrustSVD integrates multiple information sources into the recommendation model in order to reduce the data sparsity and cold start problems and their degradation of recommendation performance. An analysis of social trust data from four real-world data sets suggests that not only the explicit but also the implicit influence of both ratings and trust should be taken into consideration in a recommendation model. TrustSVD therefore builds on top of a state-of-the-art recommendation algorithm, SVD++ (which uses the explicit and implicit influence of rated items), by further incorporating both the explicit and implicit influence of trusted and trusting users on the prediction of items for an active user. The proposed technique is the first to extend SVD++ with social trust information. Experimental results on the four data sets demonstrate that TrustSVD achieves better accuracy than other ten counterparts recommendation techniques.

User-based collaborative filtering , a widely used nearest neighbour-based recommendation technique, predicts an item’s rating by aggregating its ratings from similar users. User similarity is traditionally calculated by cosine similarity or the Pearson correlation coefficient . However, both of these measures consider only the direction of rating vectors, and suffer from a range of drawbacks. To overcome these issues, we propose a novel Bayesian similarity measure based on the Dirichlet distribution, taking into consideration both the direction and length of rating vectors. We posit that not all the rating pairs should be equally counted in order to accurately model user correlation. Three different evidence factors are designed to compute the weights of rating pairs. Further, our principled method reduces correlation due to chance and potential system bias. Experimental results on six real-world datasets show that our method achieves superior accuracy in comparison with counterparts.

Online review fraud has evolved in sophistication by launching intelligent campaigns where a group of coordinated participants work together to deliver deceptive reviews for the designated targets. Such collusive fraud is considered much harder to defend against as these campaign participants are capable of evading detection by shaping their behaviors collectively so as not to appear suspicious. The present work complements existing studies by exploring more subtle behavioral trails connected with collusive review fraud. A novel statistical model is proposed to further characterize, recognize, and forecast collusive fraud in online reviews. The proposed model is completely unsupervised, which bypasses the difficulty of manual annotation required for supervised modeling. It is also highly flexible to incorporate collusion characteristics available for better modeling and prediction. Experiments on two real-world datasets demonstrate the effectiveness of the proposed method and the improvements in learning and predictive abilities.

Spam campaigns spotted in popular product review websites (e.g., amazon.com) have attracted mounting attention from both industry and academia, where a group of online posters are hired to collaboratively craft deceptive reviews for some target products. The goal is to manipulate perceived reputations of the targets for their best interests. Many efforts have been made to detect such colluders by extracting pointwise features from individual reviewers/reviewer-groups, however, pairwise features which can potentially capture the underlying correlations among colluders are either ignored or just explored insufficiently in the literature. We observed that pairwise features can be more robust to model the relationships among colluders since they, as the ingredients of spam campaigns, are correlated in nature. In this paper, we explore multiple heterogeneous pairwise features in virtue of some collusion signals found in reviewers' rating behaviors and linguistic patterns. In addition, an unsupervised and intuitive colluder detecting framework has been proposed which can benefit from these pairwise features. Extensive experiments on real dataset show the effectiveness of our method and satisfactory superiority over several competitors.

Trust is one source of information that has been widely adopted to personalize online services for users, such as in product recommendations. However, trust information is usually very sparse or unavailable for most online systems. To narrow this gap, we propose a principled approach that predicts implicit trust from users' interactions, by extending a well-known trust antecedents framework. Specifically, we consider both local and global trustworthiness of target users, and form a personalized trust metric by further taking into account the active user's propensity to trust. Experimental results on two real-world datasets show that our approach works better than contemporary counterparts in terms of trust ranking performance when direct user interactions are limited.

As the rapid development of China's e-commerce in recent years and the underlying evolution of adversarial spamming tactics, more sophisticated spamming activities may carry out in Chinese review websites. Empirical analysis, on recently crawled product reviews from a popular Chinese e-commerce website, reveals the failure of many state-of-the-art spam indicators on detecting collusive spammers. Two novel methods are then proposed: 1) a KNN-based method that considers the pairwise similarity of two reviewers based on their group-level relational information and selects k most similar reviewers for voting; 2) a more general graph-based classification method that jointly classifies a set of reviewers based on their pairwise transaction correlations. Experimental results show that both our methods promisingly outperform the indicator-only classifiers in various settings.

Lack of motivation to provide ratings and eligibility to rate generally only after purchase restrain the effectiveness of recommender systems and contribute to the well-known data sparsity and cold start problems. This paper proposes a new information source for recommender systems, called prior ratings. Prior ratings are based on users' experiences of virtual products in a mediated environment, and they can be submitted prior to purchase. A conceptual model of prior ratings is proposed, integrating the environmental factor presence whose effects on product evaluation have not been studied previously. A user study conducted in website and virtual store modalities demonstrates the validity of the conceptual model, in that users are more willing and confident to provide prior ratings in virtual environments.

In this article, we present a framework of use in electronic marketplaces that allows buying agents to model the trustworthiness of selling agents in an effective way, making use of seller ratings provided by other buying agents known as advisors. The trustworthiness of the advisors is also modeled, using an approach that combines both personal and public knowledge and allows the relative weighting to be adjusted over time. Through a series of experiments that simulate e-marketplaces, including ones where sellers may vary their behavior over time, we are able to demonstrate that our proposed framework delivers effective seller recommendations to buyers, resulting in important buyer profit. We also propose limiting seller bids as a method for promoting seller honesty, thus facilitating successful selection of sellers by buyers, and demonstrate the value of this approach through experimental results. Overall, this research is focused on the technological aspects of electronic commerce and specifically on technology that would be used to manage trust.

Reputation systems are highly prone to unfair rating attacks. Though many approaches for detecting unfair ratings have been proposed so far, their performance is often affected by the environment where they are applied. For a given unknown real environment, it is difficult to choose the most suitable approach for detecting unfair ratings as the ground truth data necessary to evaluate the accuracy of the detection approaches remains unknown. In this paper, we propose a novel Context-AwaRE (CARE) framework, to choose the most suitable unfair rating detection approach for a given unknown real environment. The framework first identifies simulated environments, closely similar to that of the unknown environment. The detection approaches performing well in the most similar simulated environments are then chosen as the suitable ones for the unknown real environment. Detailed experiments illustrate that the CARE framework can choose the most suitable detection approach to accurately distinguish fair and unfair ratings for any given unknown environment.

Similarity measurement is essential in many preference-based personalized applications such as collaborative recommendation and service selection. Up to date, current researches have mainly focused on the measurements for quantitative preference rather than qualitative preference, although the latter has attracted much attention recently. Only a very few methods to measure user similarity are proposed. This paper aims to fill in this gap by proposing an intuitive similarity measurement for conditional qualitative preference which is represented by CP-nets. Experimental results based on two expanded real-life datasets demonstrate that our similarity measurement is not only able to correctly reflect user's preference changes, but also effective to identify similar users.

PGP Web of Trust where users can sign digital signatures on public key certificates of other users has been successfully applied in securing emails and files transmitted over the Internet. However, its rigorous restrictions on utilizable trust relationships and acceptable signatures limit its performance. In this paper, we first make some modification and extension to PGP Web of Trust by relaxing those constraints. In addition, we propose a novel method to further expand trusted neighborhood of users by merging the signatures of the trusted neighbors and finding the similar users based on the merged signature set. Confirmed by the experiments carried out in different simulated real-life scenarios, our method applied to both the modified and extended PGP methods can improve their performance. With the expansion of trusted neighborhood, the performance of the original PGP Web of Trust is also improved considerably.

In this paper, we propose a novel community-based approach for web service selection where super-agents with more capabilities serve as community managers. They maintain communities and build community-based reputation for a service based on the opinions from all community members that have similar interests and judgement criteria. The community-based reputation is useful for consumer agents in selecting satisfactory services when they do not have much personal experience with the services. Experimental results show that our approach results in more effective service selection. A practical reward mechanism is also introduced to create incentives for super-agents to contribute their resources and provide truthful community-based reputation information, as strong support for our approach.

A qualitative way is desirable for web service selection according to agents' preferences on non-functional Quality of Service (QoS) attributes of services. However, it is challenging when the decision has to be made for multiple agents with preferences on attributes that may be incomplete. In this paper, we first use a qualitative graphical representation tool called CP-nets to describe preference relations in a relatively compact, intuitive and structured manner. We then propose algorithms based on this representation to select web services for multiple agents despite the presence of incompleteness in their preference orderings. Our experimental results indicate that this method can always obtain some optimal outcomes which closely satisfy all agents.

On participatory Websites, users provide opinions about products, with both overall ratings and textual reviews. In this paper, we propose an approach to accurately estimate feature ratings of the products. This approach selects user reviews that extensively discuss specific features of the products (called specialized reviews), using information distance of reviews on the features. Experiments on real data show that overall ratings of the specialized reviews can be used to represent their feature ratings. The average of these overall ratings can be used by recommender systems to provide feature specific recommendations that better help users make purchasing decisions.