Retrieval-augmented generation (RAG) is increasingly deployed in enterprise search and document-centric assistants, where responses must be grounded in long and complex source materials. In practice, verifying that generated answers faithfully reflect retrieved documents is difficult: large language models can check long contexts but are too slow and costly for interactive services, while lightweight classifiers operate within strict context limits and frequently miss evidence outside truncated passages. We present the design of a real-time verification component integrated into a production RAG pipeline that enables full-document grounding under latency constraints. The system processes documents up to 32K tokens and employs adaptive inference strategies to balance response time and verification coverage across workloads. We describe the architectural decisions, operational trade-offs, and evaluation methodology used to deploy the verifier, and show that full-context verification substantially improves detection of unsupported responses compared with truncated validation. Our experience highlights when long-context verification is necessary, why chunk-based checking often fails in real documents, and how latency budgets shape model design. These findings provide practical guidance for practitioners building reliable large-scale retrieval-augmented applications.

Inspired by the success of language models (LM), scaling up deep learning recommendation systems (DLRS) has become a recent trend in the community. All previous methods tend to scale up the model parameters during training time. However, how to efficiently utilize and scale up computational resources during test time remains underexplored, which can prove to be a scaling-efficient approach and bring orthogonal improvements in LM domains. The key point in applying test-time scaling to DLRS lies in effectively generating diverse yet meaningful outputs for the same instance. We propose two ways: One is to explore the heterogeneity of different model architectures. The other is to utilize the randomness of model initialization under a homogeneous architecture. The evaluation is conducted across eight models, including both classic and SOTA models, on three benchmarks. Sufficient evidence proves the effectiveness of both solutions. We further prove that under the same inference budget, test-time scaling can outperform parameter scaling. Our test-time scaling can also be seamlessly accelerated with the increase in parallel servers when deployed online, without affecting the inference time on the user side. Code is available here. https://github.com/aTitye/TTS4CTR.

The evolution of previous Click-Through Rate (CTR) models has mainly been driven by proposing complex components, whether shallow or deep, that are adept at modeling feature interactions. However, there has been less focus on improving fusion design. Instead, two naive solutions, stacked and parallel fusion, are commonly used. Both solutions rely on pre-determined fusion connections and fixed fusion operations. It has been repetitively observed that changes in fusion design may result in different performances, highlighting the critical role that fusion plays in CTR models. While there have been attempts to refine these basic fusion strategies, these efforts have often been constrained to specific settings or dependent on specific components. Neural architecture search has also been introduced to partially deal with fusion design, but it comes with limitations. The complexity of the search space can lead to inefficient and ineffective results. To bridge this gap, we introduce OptFusion, a method that automates the learning of fusion, encompassing both the connection learning and the operation selection. We have proposed a one-shot learning algorithm tackling these tasks concurrently. Our experiments are conducted over three large-scale datasets. Extensive experiments prove both the effectiveness and efficiency of OptFusion in improving CTR model performance. Our code implementation is available here https://github.com/kexin-kxzhang/OptFusion.

Blockchain technology, with implications in the financial domain, offers data in the form of large-scale transaction networks. Analyzing transaction networks facilitates fraud detection, market analysis, and supports government regulation. Despite many graph representation learning methods for transaction network analysis, we pinpoint two salient limitations that merit more investigation. Existing methods predominantly focus on the snapshots of transaction networks, sidelining the evolving nature of blockchain transaction networks. Existing methodologies may not sufficiently emphasize efficient, incremental learning capabilities, which are essential for addressing the scalability challenges in ever-expanding large-scale transaction networks. To address these challenges, we employed an incremental approach for random walk-based node representation learning in transaction networks. Further, we proposed a Metropolis-Hastings-based random walk mechanism for improved efficiency. The empirical evaluation conducted on blockchain transaction datasets reveals comparable performance in node classification tasks while reducing computational overhead. Potential applications include transaction network monitoring, the efficient classification of blockchain addresses for fraud detection or the identification of specialized address types within the network.

Logistics advertising is an emerging task in online-to-offline logistics systems, where logistics companies expand parcel shipping services to new users through advertisements on shopping websites. Compared to existing online e-commerce advertising, logistics advertising has two significant new characteristics: (i) the complex factors in logistics advertising considering both users' offline logistics preference and online purchasing profiles; and (ii) data sparsity and mutual relations among multiple steps due to longer advertising conversion processes. To address these challenges, we design MCAC, a Multi-task Conditional Attention network-based logistics advertising Conversion prediction framework, which consists of (i) an offline shipping preference extraction model to extract the user's offline logistics preference from historical shipping records, and (ii) a multi-task conditional attention-based conversion rate prediction module to model mutual relations among multiple steps in logistics advertising conversion processes. We evaluate and deploy MCAC on one of the largest e-commerce platforms in China for logistics advertising. Extensive offline experiments show that our method outperforms state-of-the-art baselines in various metrics. Moreover, the conversion rate prediction results of large-scale online A/B testing show that MCAC achieves a 15.22% improvement compared to existing industrial practices, which demonstrates the effectiveness of the proposed framework.

Blockchain and smart contracts are one of the key technologies promoting Web 3.0. However, due to security considerations and consistency requirements, smart contracts currently only support simple and deterministic programs, which significantly hinders their deployment in intelligent Web 3.0 applications. To enhance smart contracts intelligence on the blockchain, we propose SMART, a plug-in smart contract framework that supports efficient AI model inference while being compatible with existing blockchains. To handle the high complexity of model inference, we propose an on-chain and off-chain joint execution model, which separates the SMART contract into two parts: the deterministic code still runs inside an on-chain virtual machine, while the complex model inference is offloaded to off-chain compute nodes. To solve the non-determinism brought by model inference, we leverage Trusted Execution Environments (TEEs) to endorse the integrity and correctness of the off-chain execution. We also design distributed attestation and secret key provisioning schemes to further enhance the system security and model privacy. We implement a SMART prototype and evaluate it on a popular Ethereum Virtual Machine (EVM)-based blockchain. Theoretical analysis and prototype evaluation show that SMART not only achieves the security goals of correctness, liveness, and model privacy, but also has approximately 5 orders of magnitude faster inference efficiency than existing on-chain solutions.

Diversifying return results is an important research topic in retrieval systems in order to satisfy both the various interests of customers and the equal market exposure of providers. There has been growing attention on diversity-aware research during recent years, accompanied by a proliferation of literature on methods to promote diversity in search and recommendation. However, diversity-aware studies in retrieval systems lack a systematic organization and are rather fragmented. In this survey, we are the first to propose a unified taxonomy for classifying the metrics and approaches of diversification in both search and recommendation, which are two of the most extensively researched fields of retrieval systems. We begin the survey with a brief discussion of why diversity is important in retrieval systems, followed by a summary of the various diversity concerns in search and recommendation, highlighting their relationship and differences. For the survey's main body, we present a unified taxonomy of diversification metrics and approaches in retrieval systems, from both the search and recommendation perspectives. In the later part of the survey, we discuss the open research questions of diversity-aware research in search and recommendation in an effort to inspire future innovations and encourage the implementation of diversity in real-world systems.

To offer accurate and diverse recommendation services, recent methods use auxiliary information to foster the learning process of user and item representations. Many state-of-the-art (SOTA) methods fuse different sources of information (user, item, knowledge graph, tags, etc.) into a graph and use Graph Neural Networks (GNNs) to introduce the auxiliary information through the message passing paradigm. In this work, we seek an alternative framework that is light and effective through self-supervised learning across different sources of information, particularly for the commonly accessible item tag information. We use a self-supervision signal to pair users with the auxiliary information (tags) associated with the items they have interacted with before. To achieve the pairing, we create a proxy training task. For a given item, the model predicts which is the correct pairing between the representations obtained from the users that have interacted with this item and the tags assigned to it. This design provides an efficient solution, using the auxiliary information directly to enhance the quality of user and item embeddings. User behavior in recommendation systems is driven by the complex interactions of many factors behind the users’ decision-making processes. To make the pairing process more fine-grained and avoid embedding collapse, we propose a user intent-aware self-supervised pairing process where we split the user embeddings into multiple sub-embedding vectors. Each sub-embedding vector captures a specific user intent via self-supervised alignment with a particular cluster of tags. We integrate our designed framework with various recommendation models, demonstrating its flexibility and compatibility. Through comparison with numerous SOTA methods on seven real-world datasets, we show that our method can achieve better performance while requiring less training time. This indicates the potential of applying our approach on web-scale datasets.

Click-through prediction (CTR) models transform features into latent vectors and enumerate possible feature interactions to improve performance based on the input feature set. Therefore, when selecting an optimal feature set, we should consider the influence of both features and their interaction. However, most previous works focus on either feature field selection or only select feature interaction based on the fixed feature set to produce the feature set. The former restricts search space to the feature field, which is too coarse to determine subtle features. They also do not filter useless feature interactions, leading to higher computation costs and degraded model performance. The latter identifies useful feature interaction from all available features, resulting in many redundant features in the feature set. In this paper, we propose a novel method named OptFS to address these problems. To unify the selection of features and their interaction, we decompose the selection of each feature interaction into the selection of two correlated features. Such a decomposition makes the model end-to-end trainable given various feature interaction operations. By adopting feature-level search space, we set a learnable gate to determine whether each feature should be within the feature set. Because of the large-scale search space, we develop a learning-by-continuation training scheme to learn such gates. Hence, OptFS generates the feature set containing features that improve the final prediction results. Experimentally, we evaluate OptFS on three public datasets, demonstrating OptFS can optimize feature sets which enhance the model performance and further reduce both the storage and computational cost.

Nowadays, most online services are hosted on multi-stakeholder marketplaces, where consumers and producers may have different objectives. Conventional recommendation systems, however, mainly focus on maximizing consumers’ satisfaction by recommending the most relevant items to each individual. This may result in unfair exposure of items, thus jeopardizing producer benefits. Additionally, they do not care whether consumers from diverse demographic groups are equally satisfied. To address these limitations, we propose a multi-objective optimization framework for fairness-aware recommendation,Multi-FR, that adaptively balances accuracy and fairness for various stakeholders with Pareto optimality guarantee. We first propose four fairness constraints on consumers and producers. In order to train the whole framework in an end-to-end way, we utilize the smooth rank and stochastic ranking policy to make these fairness criteria differentiable and friendly to back-propagation. Then, we adopt the multiple gradient descent algorithm to generate a Pareto set of solutions, from which the most appropriate one is selected by the Least Misery Strategy. The experimental results demonstrate thatMulti-FRlargely improves recommendation fairness on multiple stakeholders over the state-of-the-art approaches while maintaining almost the same recommendation accuracy. The training efficiency study confirms our model’s ability to simultaneously optimize different fairness constraints for many stakeholders efficiently.

Click-through rate (CTR) prediction model usually consists of three components: embedding table, feature interaction layer, and classifier. Learning embedding table plays a fundamental role in CTR prediction from the view of the model performance and memory usage. The embedding table is a two-dimensional tensor, with its axes indicating the number of feature values and the embedding dimension, respectively. To learn an efficient and effective embedding table, recent works either assign various embedding dimensions for feature fields and reduce the number of embeddings respectively or mask the embedding table parameters. However, all these existing works cannot get an optimal embedding table. On the one hand, various embedding dimensions still require a large amount of memory due to the vast number of features in the dataset. On the other hand, decreasing the number of embeddings usually suffers from performance degradation, which is intolerable in CTR prediction. Finally, pruning embedding parameters will lead to a sparse embedding table, which is hard to be deployed. To this end, we propose an optimal embedding table learning framework OptEmbed, which provides a practical and general method to find an optimal embedding table for various base CTR models. Specifically, we propose pruning the redundant embeddings regarding corresponding features' importance by learnable pruning thresholds. Furthermore, we consider assigning various embedding dimensions as one single candidate architecture. To efficiently search the optimal embedding dimensions, we design a uniform embedding dimension sampling scheme to equally train all candidate architectures, meaning architecture-related parameters and learnable thresholds are trained simultaneously in one supernet. We then propose an evolution search method based on the supernet to find the optimal embedding dimensions for each field. Experiments on public datasets show that OptEmbed can learn a compact embedding table which can further improve the model performance.

Implicit feedback is frequently used for developing personalized recommendation services due to its ubiquity and accessibility in real-world systems. In order to effectively utilize such information, most research adopts the pairwise ranking method on constructed training triplets (user, positive item, negative item) and aims to distinguish between positive items and negative items for each user. However, most of these methods treat all the training triplets equally, which ignores the subtle difference between different positive or negative items. On the other hand, even though some other works make use of the auxiliary information (e.g., dwell time) of user behaviors to capture this subtle difference, such auxiliary information is hard to obtain. To mitigate the aforementioned problems, we propose a novel training framework named Triplet Importance Learning (TIL), which adaptively learns the importance score of training triplets. We devise two strategies for the importance score generation and formulate the whole procedure as a bilevel optimization, which does not require any rule-based design. We integrate the proposed training procedure with several Matrix Factorization (MF)- and Graph Neural Network (GNN)-based recommendation models, demonstrating the compatibility of our framework. Via a comparison using three real-world datasets with many state-of-the-art methods, we show that our proposed method outperforms the best existing models by 3-21% in terms of [email protected] for the top-k recommendation.

Click-through rate prediction is one of the core tasks in commercial recommender systems. It aims to predict the prob-ability of a user clicking a particular item given user and item features. As feature interactions bring in non-linearity, they are widely adopted to improve the performance of CTR prediction models. Therefore, effectively modelling feature interactions has attracted much attention in both the research and industry field. The current approaches can generally be categorized into three classes: (i) naïve methods, which do not model feature interactions and only use original features; (ii) memorized methods, which memorize feature interactions by explicitly viewing them as new features and assigning trainable embeddings; (iii) factorized meth-ods, which learn latent vectors for original features and implicitly model feature interactions through factorization functions. Studies have shown that modelling feature interactions by one of these methods alone are suboptimal due to the unique characteristics of different feature interactions. To address this issue, we first propose a general framework called OptInter which finds the most suitable modelling method for each feature interaction. Different state-of-the-art deep CTR models can be viewed as instances of OptInter. To realize the functionality of OptInter, we also introduce a learning algorithm that automatically searches for the optimal modelling method. We conduct extensive experiments on four large datasets, including three public and one private. Experimental results demonstrate the effectiveness of OptInter. Because our OptInter finds the optimal modelling method for each feature interaction, our experiments show that OptInter improves the best performed state-of-the-art baseline deep CTR models by up to 2.21%. Compared to the memorized method, which also outperforms baselines, we reduce up to 91% parameters. In addition, we conduct several ablation studies to investigate the influence of different components of OptInter. Finally, we provide interpretable discussions on the results of OptInter.

Prior research on exposure fairness in the context of recommender systems has focused mostly on disparities in the exposure of individual or groups of items to individual users of the system. The problem of how individual or groups of items may be systemically under or over exposed to groups of users, or even all users, has received relatively less attention. However, such systemic disparities in information exposure can result in observable social harms, such as withholding economic opportunities from historically marginalized groups (allocative harm) or amplifying gendered and racialized stereotypes (representational harm). Previously, Diaz et al. developed the expected exposure metric---that incorporates existing user browsing models that have previously been developed for information retrieval---to study fairness of content exposure to individual users. We extend their proposed framework to formalize a family of exposure fairness metrics that model the problem jointly from the perspective of both the consumers and producers. Specifically, we consider group attributes for both types of stakeholders to identify and mitigate fairness concerns that go beyond individual users and items towards more systemic biases in recommendation. Furthermore, we study and discuss the relationships between the different exposure fairness dimensions proposed in this paper, as well as demonstrate how stochastic ranking policies can be optimized towards said fairness goals.

Personalized recommender systems are playing an increasingly important role as more content and services become available and users struggle to identify what might interest them. Although matrix factorization and deep learning based methods have proved effective in user preference modeling, they violate the triangle inequality and fail to capture fine-grained preference information. To tackle this, we develop a distance-based recommendation model with several novel aspects: (i) each user and item are parameterized by Gaussian distributions to capture the learning uncertainties; (ii) an adaptive margin generation scheme is proposed to generate the margins regarding different training triplets; (iii) explicit user-user/item-item similarity modeling is incorporated in the objective function. The Wasserstein distance is employed to determine preferences because it obeys the triangle inequality and can measure the distance between probabilistic distributions. Via a comparison using five real-world datasets with state-of-the-art methods, the proposed model outperforms the best existing models by 4-22% in terms of [email protected] on Top-K recommendation.

To fully support the emerging location-aware applications, location information with meter-level resolution (or even higher) is required anytime and anywhere. Unfortunately, most of the current location sources (e.g., GPS and check-in data) either are unavailable indoor or provide only house-level resolutions. To fill the gap, this paper utilizes the ubiquitous WiFi signals to establish a (sub)meter-level localization system, which employs WiFi propagation characteristics as location fingerprints. However, an unsolved issue of these WiFi fingerprints lies in their inconsistency across different users. In other words, WiFi fingerprints collected from one user may not be used to localize another user. To address this issue, we propose a WiFi-based Domain-adaptive system FiDo, which is able to localize many different users with labelled data from only one or two example users. FiDo contains two modules: 1) a data augmenter that introduces data diversity using a Variational Autoencoder (VAE); and 2) a domain-adaptive classifier that adjusts itself to newly collected unlabelled data using a joint classification-reconstruction structure. Compared to the state of the art, FiDo increases average F1 score by 11.8% and improves the worst-case accuracy by 20.2%.

The chronological order of user-item interactions is a key feature in many recommender systems, where the items that users will interact may largely depend on those items that users just accessed recently. However, with the tremendous increase of users and items, sequential recommender systems still face several challenging problems: (1) the hardness of modeling the long-term user interests from sparse implicit feedback; (2) the difficulty of capturing the short-term user interests given several items the user just accessed. To cope with these challenges, we propose a hierarchical gating network (HGN), integrated with the Bayesian Personalized Ranking (BPR) to capture both the long-term and short-term user interests. Our HGN consists of a feature gating module, an instance gating module, and an item-item product module. In particular, our feature gating and instance gating modules select what item features can be passed to the downstream layers from the feature and instance levels, respectively. Our item-item product module explicitly captures the item relations between the items that users accessed in the past and those items users will access in the future. We extensively evaluate our model with several state-of-the-art methods and different validation metrics on five real-world datasets. The experimental results demonstrate the effectiveness of our model on Top-N sequential recommendation.

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

Many approaches focus on detecting dense blocks in the tensor of multimodal data to prevent fraudulent entities (e.g., accounts, links) from retweet boosting, hashtag hijacking, link advertising, etc. However, no existing method is effective to find the dense block if it only possesses high density on a subset of all dimensions in tensors. In this paper, we novelly identify dense-block detection with dense-subgraph mining, by modeling a tensor into a weighted graph without any density information lost. Based on the weighted graph, which we call information sharing graph (ISG), we propose an algorithm for finding multiple densest subgraphs, D-Spot, that is faster (up to 11x faster than the state-of-the-art algorithm) and can be computed in parallel. In an N-dimensional tensor, the entity group found by the ISG+D-Spot is at least 1/2 of the optimum with respect to density, compared with the 1/N guarantee ensured by competing methods. We use nine datasets to demonstrate that ISG+D-Spot becomes new state-of-the-art dense-block detection method in terms of accuracy specifically for fraud detection.

The rapid growth of Location-based Social Networks (LBSNs) provides a great opportunity to satisfy the strong demand for personalized Point-of-Interest (POI) recommendation services. However, with the tremendous increase of users and POIs, POI recommender systems still face several challenging problems: (1) the hardness of modeling complex user-POI interactions from sparse implicit feedback; (2) the difficulty of incorporating the geographical context information. To cope with these challenges, we propose a novel autoencoder-based model to learn the complex user-POI relations, namely SAE-NAD, which consists of a self-attentive encoder (SAE) and a neighbor-aware decoder (NAD). In particular, unlike previous works equally treat users' checked-in POIs, our self-attentive encoder adaptively differentiates the user preference degrees in multiple aspects, by adopting a multi-dimensional attention mechanism. To incorporate the geographical context information, we propose a neighbor-aware decoder to make users' reachability higher on the similar and nearby neighbors of checked-in POIs, which is achieved by the inner product of POI embeddings together with the radial basis function (RBF) kernel. To evaluate the proposed model, we conduct extensive experiments on three real-world datasets with many state-of-the-art methods and evaluation metrics. The experimental results demonstrate the effectiveness of our model.

It has been recently shown that deep neural networks (DNNs) are susceptible to a particular type of attack that exploits a fundamental flaw in their design. This attack consists of generating particular synthetic examples referred to as adversarial samples. These samples are constructed by slightly manipulating real data-points that change "fool" the original DNN model, forcing it to misclassify previously correctly classified samples with high confidence. Many believe addressing this flaw is essential for DNNs to be used in critical applications such as cyber security. Previous work has shown that learning algorithms that enhance the robustness of DNN models all use the tactic of "security through obscurity". This means that security can be guaranteed only if one can obscure the learning algorithms from adversaries. Once the learning technique is disclosed, DNNs protected by these defense mechanisms are still susceptible to adversarial samples. In this work, we investigate by examining how previous research dealt with this and propose a generic approach to enhance a DNN's resistance to adversarial samples. More specifically, our approach integrates a data transformation module with a DNN, making it robust even if we reveal the underlying learning algorithm. To demonstrate the generality of our proposed approach and its potential for handling cyber security applications, we evaluate our method and several other existing solutions on datasets publicly available, such as a large scale malware dataset and MNIST and IMDB datasets. Our results indicate that our approach typically provides superior classification performance and robustness to attacks compared with state-of-art solutions.

Mobile dating applications such as Coffee Meets Bagel, Tantan, and Tinder, have become significant for young adults to meet new friends and discover romantic relationships. From a system designer's perspective, in order to achieve better user experience in these applications, we should take both the efficiency and fairness of a dating market into consideration, so as to increase the overall satisfaction for all users. Towards this goal, we investigate the nature of diminishing marginal returns for online dating markets (i.e., captured by the submodularity), and trade-off between the efficiency and fairness of the market with Nash social welfare. We further design effective online algorithms to the apps. We verify our models and algorithms through sound theoretical analysis and empirical studies by using real data and show that our algorithms can significantly improve the ecosystems of the online dating applications.

Outside the highly publicized victories in the game of Go, there have been numerous successful applications of deep learning in the fields of information retrieval, computer vision, and speech recognition. In cybersecurity, an increasing number of companies have begun exploring the use of deep learning (DL) in a variety of security tasks with malware detection among the more popular. These companies claim that deep neural networks (DNNs) could help turn the tide in the war against malware infection. However, DNNs are vulnerable to adversarial samples, a shortcoming that plagues most, if not all, statistical and machine learning models. Recent research has demonstrated that those with malicious intent can easily circumvent deep learning-powered malware detection by exploiting this weakness.

Recently, map services (e.g., Google maps) and location-based online social networks (e.g., Foursquare) attract a lot of attention and businesses. With the increasing popularity of these location-based services, exploring and characterizing points of interests (PoIs) such as restaurants and hotels on maps provides valuable information for applications such as start-up marketing research. Due to the lack of a direct fully access to PoI databases, it is infeasible to exhaustively search and collect all PoIs within a large area using public APIs, which usually impose a limit on the maximum query rate. In this paper, we propose sampling methods to accurately estimate PoI statistics such as sum and average aggregates from as few queries as possible. Experimental results based on real datasets show that our methods are efficient, and require six times less queries than state-of-the-art methods to achieve the same accuracy.

The widespread of adult content on online social networks (e.g., Twitter) is becoming an emerging yet critical problem. An automatic method to identify accounts spreading sexually explicit content (i.e., adult account) is of significant values in protecting children and improving user experiences. Traditional adult content detection techniques are ill-suited for detecting adult accounts on Twitter due to the diversity and dynamics in Twitter content. In this paper, we formulate the adult account detection as a graph based classification problem and demonstrate our detection method on Twitter by using social links between Twitter accounts and entities in tweets. As adult Twitter accounts are mostly connected with normal accounts and post many normal entities, which makes the graph full of noisy links, existing graph based classification techniques cannot work well on such a graph. To address this problem, we propose an iterative social based classifier (ISC), a novel graph based classification technique resistant to the noisy links. Evaluations using large-scale real-world Twitter data show that, by labeling a small number of popular Twitter accounts, ISC can achieve satisfactory performance in adult account detection, significantly outperforming existing techniques.

Recently map services (e.g., Google maps) and location-based online social networks (e.g., Foursquare) attract a lot of attention and businesses. With the increasing popularity of these location-based services, exploring and characterizing points of interests (PoIs) such as restaurants and hotels on maps provides valuable information for applications such as start-up marketing research. Due to the lack of a direct fully access to PoI databases, it is infeasible to exhaustively search and collect all PoIs within a large area using public APIs, which usually impose a limit on the maximum query rate. In this paper, we propose an effective and efficient method to sample PoIs on maps, and give unbiased estimators to calculate PoI statistics such as sum and average aggregates. Experimental results based on real datasets show that our method is efficient, and requires six times less queries than state-of-the-art methods to achieve the same accuracy.

The need for highly scalable and accurate detection and filtering of misbehaving users and obscene content in online video chat services has grown as the popularity of these services has exploded in popularity. This is a challenging problem because processing large amounts of video is compute intensive, decisions about whether a user is misbehaving or not must be made online and quickly, and moreover these video chats are characterized by low quality video, poorly lit scenes, diversity of users and their behaviors, diversity of the content, and typically short sessions. This paper presents EMeralD, a highly scalable system for accurately detecting and filtering misbehaving users in online video chat applications. EMeralD substantially improves upon the state-of-the-art filtering mechanisms by achieving much lower computational cost and higher accuracy. We demonstrate EMeralD's improvement via experimental evaluations on real-world data sets obtained from Chatroulette.com.

Online video chat services, such as Chatroulette, Omegle, and vChatter are becoming increasingly popular and have attracted millions of users. One critical problem encountered in such applications is the presence of misbehaving users ("flashers") and obscene content. Automatically filtering out obscene content from these systems in an efficient manner poses a difficult challenge. This paper presents a novel Fine-Grained Cascaded (FGC) classification solution that significantly speeds up the compute-intensive process of classifying misbehaving users by dividing image feature extraction into multiple stages and filtering out easily classified images in earlier stages, thus saving unnecessary computation costs of feature extraction in later stages. Our work is further enhanced by integrating new webcam-related contextual information (illumination and color) into the classification process, and a 2-stage soft margin SVM algorithm for combining multiple features. Evaluation results using real-world data set obtained from Chatroulette show that the proposed FGC based classification solution significantly outperforms state-of-the-art techniques.

Online video chat services such as Chatroulette, Omegle, and vChatter that randomly match pairs of users in video chat sessions are fast becoming very popular, with over a million users per month in the case of Chatroulette. A key problem encountered in such systems is the presence of flashers and obscene content. This problem is especially acute given the presence of underage minors in such systems. This paper presents SafeVchat, a novel solution to the problem of flasher detection that employs an array of image detection algorithms. A key contribution of the paper concerns how the results of the individual detectors are fused together into an overall decision classifying the user as misbehaving or not, based on Dempster-Shafer Theory. The paper introduces a novel, motion-based skin detection method that achieves significantly higher recall and better precision. The proposed methods have been evaluated over real-world data and image traces obtained from Chatroulette.com.

Faceted search is becoming a popular method to allow users to interactively search and navigate complex information spaces. A faceted search system presents users with key-value metadata that is used for query refinement. While popular in e-commerce and digital libraries, not much research has been conducted on which metadata to present to a user in order to improve the search experience. Nor are there repeatable benchmarks for evaluating a faceted search engine. This paper proposes the use of collaborative filtering and personalization to customize the search interface to each user's behavior. This paper also proposes a utility based framework to evaluate the faceted interface. In order to demonstrate these ideas and better understand personalized faceted search, several faceted search algorithms are proposed and evaluated using the novel evaluation methodology.