Sequential recommendation predicts the next items a user will interact with by modeling evolving preferences over time. Recent diffusion-based generative recommenders show promise in capturing complex dependencies, but they typically treat temporal context as an external conditioning signal rather than integrating temporal transitions into the diffusion dynamics. In this paper, we introduce TDRec (Temporally-aware Diffusion for sequential Recommendation), a novel framework that integrates temporal progression into both forward and reverse processes: at each diffusion step, a position's latent is updated by noise injection and by mixing with its preceding latent. We derive a closed-form solution for this temporal mixing process, proving that it allows for efficient parallel training with O(1) complexity relative to sequence length. Furthermore, we establish the existence of a corresponding DDPM-like reverse process and a reparameterized objective, ensuring efficient optimization and sampling without incurring extra computational overhead. Empirical results on three public datasets demonstrate that TDRec consistently outperforms state-of-the-art baselines, including recent diffusion models. Ablation studies confirm the effectiveness of the temporal scheduler and sequence-reduction module in generating coherent, context-aware predictions. Code is available at https://github.com/wuyaoericyy/TDRec.

By allowing each client to refer to the knowledge from other clients while retaining their specific characteristics, partial knowledge sharing has become one of the main approaches to realizing personalized federated learning (pFL). Representative techniques of partial knowledge sharing propose sharing the feature extractor while customizing the classifier head of the neural network. Although such methods achieve great success, the underlying principle behind them remains yet to be comprehensively understood. A fundamental problem is whether it is really appropriate to fully share the feature extractor. Based on the theory of neural collapse, in this paper, we demonstrate both theoretically and empirically that the feature extractor should be partially shared rather than fully shared. More specifically, we identify a substantial inconsistency between the fused global feature representations and expected local feature representations, and thus it is necessary to preserve partially customized layers of the feature extractor for enhancing personalized representations. Based on this discovery, we further propose a novel method called pFedDKS which detaches the shared global knowledge and customized local knowledge by providing detached feature prototypes. Extensive experiments on various datasets and models show that pFedDKS outperforms state-of-the-arts.

Graph contrastive learning (GCL) is a powerful self-supervised learning approach. However, existing GCL methods are designed for homophilic graphs, using low-pass filters that struggle to capture high-frequency components in heterophilic graphs. We proposeGraphContrastiveLearning withRegularization and stabilization techniques enhanced high-passFilter (GCLRF).REgularization andStabilization techniques enhancedHigh-pass filter (RESH) can serve as a mutually promoting plug-in, significantly improving the performance of various homophilic GCL training strategies on heterophilic graphs. We also investigate four component orderings in RESH and identify the optimal fusion mechanism, demonstrating its critical impact on performance. Experiments show GCLRF achieves state-of-the-art (SOTA) performance across six benchmark datasets in node classification and clustering. Notably, on the Cornell dataset, GCLRF outperformers classification accuracy by 6.76% and achieves a 23.64%relative improvement in clustering normalized mutual information (NMI).

With the rise of generative paradigms, generative recommendation has garnered increasing attention. The core component is the item code , generally derived by quantizing collaborative or semantic representations to serve as candidate items identifiers in the context. However, existing methods typically construct separate codes for each modality, leading to higher computational and storage costs and hindering the integration of their complementary strengths. Considering this limitation, we seek to integrate two different modalities into a unified code , fully unleashing the potential of complementary nature among modalities. Nevertheless, the integration remains challenging: the integrated embedding obtained by the common concatenation method would lead to underutilization of collaborative knowledge, thereby resulting in limited effectiveness. To address this, we propose a novel method, named UNGER, which integrates semantic and collaborative knowledge into a UNified code for Generative Recommendation . Specifically, we propose to adaptively learn an integrated embedding through the joint optimization of cross-modality knowledge alignment and next-item prediction tasks. Subsequently, to mitigate the information loss caused by the quantization process, we introduce an intra-modality knowledge distillation task, using the integrated embeddings as supervised signals to compensate. Extensive experiments on three widely used benchmarks demonstrate the superiority of our approach compared to existing methods.

Sequential recommendation (SR) aims to capture dynamic user preferences from users' historical behaviors. Recently, benefiting from astonishing understanding ability of pre-trained language models (PLMs), text-enhanced sequential recommender becomes a promising direction, which employs PLMs to extract semantic information for user/item representation. Although promising in improving performance and transferability, few existing text-enhanced SR studies have analyzed the differences between PLMs and recommenders, restricting the ability of PLMs for recommendation. In this paper, we make an in-depth comparison and conclude their discrepancies in representation and knowledge level, respectively, caused by different multi-modal content and task-oriented capabilities. Based on this, we propose a Recommendation-Oriented Language Model Adaptation framework (named ROMA) using multi-modal multi-domain item sequences. To empower PLMs with a rational understanding of user/item modeling and the recommendation task, ROMA partitions a PLM into bottom and top layers, respectively, allowing representation-level and task-level adaptation with elaborately designed architectures, transferring strategy and learning framework. Our experimental results on public benchmarks demonstrate the effectiveness and transferability of our framework. Additionally, we showcase the application value of ROMA on the recommender system of Huawei's AppGallery through online A/B testing, which shows significant improvements in online metrics.

Nowadays, Graph Fraud Detection (GFD) in financial scenarios has become an urgent research topic to protect online payment security. However, as organized crime groups are becoming more professional in real-world scenarios, fraudsters are employing more sophisticated camouflage strategies. Specifically, fraudsters disguise themselves by mimicking the behavioral data collected by platforms, ensuring that their key characteristics are consistent with those of benign users to a high degree, which we call Adaptive Camouflage. Consequently, this narrows the differences in behavioral traits between them and benign users within the platform's database, thereby making current GFD models lose efficiency. To address this problem, we propose a relation diffusion-based graph augmentation model Grad. In detail, Grad leverages a supervised graph contrastive learning module to enhance the fraud-benign difference and employs a guided relation diffusion generator to generate auxiliary homophilic relations from scratch. Based on these, weak fraudulent signals would be enhanced during the aggregation process, thus being obvious enough to be captured. Extensive experiments have been conducted on two real-world datasets provided by WeChat Pay, one of the largest online payment platforms with billions of users, and three public datasets. The results show that our proposed model Grad outperforms SOTA methods in both various scenarios, achieving at most 11.10% and 43.95% increases in AUC and AP, respectively.

The field of graph foundation models (GFMs) has seen a dramatic rise in interest in recent years. Their powerful generalization ability is believed to be endowed by self-supervised pre-training and downstream tuning techniques. There is a wide variety of knowledge patterns embedded in the graph data, such as node properties and clusters, which are crucial for learning generalized representations for GFMs. We present a comprehensive survey of self-supervised GFMs from a novel knowledge-based perspective. Our main contribution is a knowledge-based taxonomy that categorizes self-supervised graph models by the specific graph knowledge utilized: microscopic (nodes, links, etc.), mesoscopic (context, clusters, etc.), and macroscopic (global structure, manifolds, etc.). It covers a total of 9 knowledge categories and 300 references for self-supervised pre-training as well as various downstream tuning strategies. Such a knowledge-based taxonomy allows us to more clearly re-examine potential GFM architectures, including large language models (LLMs), as well as provide deeper insights for constructing future GFMs.

In recommender systems, the patterns of user behaviors (e.g., purchase, click) may vary greatly in different contexts (e.g., time and location). This is because user behavior is jointly determined by two types of factors: intrinsic factors , which reflect consistent user preference, and extrinsic factors , which reflect external incentives that may vary in different contexts. Differentiating between intrinsic and extrinsic factors helps learn user behaviors better. However, existing studies have only considered differentiating them from a single, pre-defined context (e.g., time or location), ignoring the fact that a user’s extrinsic factors may be influenced by the interplay of various contexts at the same time. In this article, we propose the intrinsic-extrinsic disentangled recommendation (IEDR) model, a generic framework that differentiates intrinsic from extrinsic factors considering various contexts simultaneously, enabling more accurate differentiation of factors and hence the improvement of recommendation accuracy. IEDR contains a context-invariant contrastive learning component to capture intrinsic factors, and a disentanglement component to extract extrinsic factors under the interplay of various contexts. The two components work together to achieve effective factor learning. Extensive experiments on real-world datasets demonstrate IEDR’s effectiveness in learning disentangled factors and significantly improving recommendation accuracy by up to 4% in NDCG.

Learning high-quality item embeddings is crucial for recommendation tasks such as matching and ranking. However, existing methods often rely on ID-based item embeddings learned end-to-end with downstream recommendation models, which may suffer from overfitting and limited generalizability. In this paper, we aim to learn universal item embeddings (dubbed UniEmbedding) that capture multi-modal semantics, generalize across multiple domains, and serve different downstream tasks. To achieve this goal, we introduce the UniEmbedding pretraining framework, which includes three modules: a domain-aware multi-modal adapter, a user-view projection module, and contrastive learning objectives across domains. Compared to naive ID embeddings, UniEmbedding provides rich semantic information that generalizes more effectively across domains. Unlike multi-modal embeddings directly extracted from off-the-shelf pretrained models, UniEmbedding achieves better alignment between content semantics and behaviors. We evaluated UniEmbedding on both public and industrial datasets, demonstrating its effectiveness in matching and ranking tasks. Furthermore, UniEmbedding has been deployed in multiple recommendation applications at Huawei, resulting in significant gains in user engagement metrics.

Huawei collaborates with some Chinese large busi-ness companies to store and process exabytes of nationwide operational data in data lake storage to provide business insights. Specifically, our customers will ask to store and process massive log message data to support their real-time and decision-making applications. Thus, we need computation and storage components in the analytic platform to process and store these data cost-efficiently. To meet these user requirements, we have designed a storage system in data lake, StreamLake, which introduces a novel design to serve log message streaming and batch data processing in distributed storage, with high scalability, efficiency, reliability and low cost. Specifically, we introduce a stream (storage) object as a storage abstraction for message streaming data to achieve the storage-disaggregated architecture with high scalability and reliability. Moreover, we utilize the erasure coding and tiered storage to save the storage cost, and furthermore, the stream object can be automatically converted to a table object such that cost-effective stream and batch data processing can be achieved. For tabular data, we implement the lakehouse functionality to support ACID via the table object, with a metadata acceleration to improve the efficiency of data access between the compute and storage engines. Also, we design a LakeBrain optimizer at the storage side to optimize the query performance and resource utilization under the storage-disaggregated architecture. Finally, we have also deployed StreamLake in China Mobile, the world's largest mobile network operator to serve over 20PB production data, and the results demonstrate improvements of 30% to 4x in terms of query performance and over 37% in terms of cost saving.

Personalized recommendation serves as a ubiquitous channel for users to discover information tailored to their interests. However, traditional recommendation models primarily rely on unique IDs and categorical features for user-item matching, potentially overlooking the nuanced essence of raw item contents across multiple modalities such as text, image, audio, and video. This underutilization of multimodal data poses a limitation to recommender systems, especially in multimedia services like news, music, and short-video platforms. The recent advancements in large multimodal models offer new opportunities and challenges in developing content-aware recommender systems. This survey seeks to provide a comprehensive exploration of the latest advancements and future trajectories in multimodal pretraining, adaptation, and generation techniques, as well as their applications in enhancing recommender systems. Furthermore, we discuss current open challenges and opportunities for future research in this dynamic domain. We believe that this survey, alongside the curated resources, will provide valuable insights to inspire further advancements in this evolving landscape.

Knowledge Graphs (KGs) enhance recommendations by providing external connectivity between items. However, there is limited research on distilling relevant knowledge in sequential recommendation, where item connections can change over time. To address this, we introduce the Temporal Knowledge Graph (TKG), which incorporates such dynamic features of user behaviors into the original KG while emphasizing sequential relationships. The TKG captures both patterns of entity dynamics (nodes) and structural dynamics (edges). Considering real-world applications with large-scale and rapidly evolving user behavior patterns, we propose an efficient two-phase framework called TKG-SRec, which strengthens Sequential Recommendation with Temporal KGs. In the first phase, we learn dynamic entity embeddings using our novel Knowledge Evolution Network (KEN) that brings together pretrained static knowledge with evolving temporal knowledge. In the second stage, downstream sequential recommender models utilize these time-specific dynamic entity embeddings with compatible neural backbones like GRUs, Transformers, and MLPs. From our extensive experiments over four datasets, TKG-SRec outperforms the current state-of-the-art by a statistically significant 5% on average. Detailed analysis validates that such filtered temporal knowledge better adapts entity embedding for sequential recommendation. In summary, TKG-SRec provides an effective and efficient approach.

Sequential recommendation (SR) models are typically trained on user-item interactions which are affected by the system exposure bias, leading to the user preference learned from the biased SR model not being fully consistent with the true user preference. Exposure bias refers to the fact that user interactions are dependent upon the partial items exposed to the user. Existing debiasing methods do not make full use of the system exposure data and suffer from sub-optimal recommendation performance and high variance.

For better performance and less resource consumption, multi-scenario recommendation (MSR) is proposed to train a unified model to serve all scenarios by leveraging data from multiple scenarios. Current works in MSR focus on designing effective networks for better information transfer among different scenarios. However, they omit two important issues when applying MSR models in industrial situations. The first is the efficiency problem brought by mixed data, which delays the update of models and further leads to performance degradation. The second is that MSR models are insensitive to the changes of distribution over time, resulting in suboptimal effectiveness in the incoming data. In this paper, we propose an incremental learning approach for MSR (IncMSR), which can not only improve the training efficiency but also perceive changes in distribution over time. Specifically, we first quantify the pair-wise distance between representations from scenario, time and time-scenario dimensions respectively. Then, we decompose the MSR model into scenario-shared and scenario-specific parts and apply fine-grained constraints on the distances quantified with respect to the two different parts. Finally, all constraints are fused in an elegant way using a metric learning framework as a supplementary penalty term to the original MSR loss function. Offline experiments on two real-world datasets are conducted to demonstrate the superiority and compatibility of our proposed approach.

The emergence of large language models (LLMs) has revolutionized the capabilities of text comprehension and generation. Multi-modal generation attracts great attention from both the industry and academia, but there is little work on personalized generation, which has important applications such as recommender systems. This paper proposes the first method for personalized multimodal generation using LLMs, showcases its applications and validates its performance via an extensive experimental study on two datasets. The proposed method, Personalized Multimodal Generation (PMG for short) first converts user behaviors (e.g., clicks in recommender systems or conversations with a virtual assistant) into natural language to facilitate LLM understanding and extract user preference descriptions. Such user preferences are then fed into a generator, such as a multimodal LLM or diffusion model, to produce personalized content. To capture user preferences comprehensively and accurately, we propose to let the LLM output a combination of explicit keywords and implicit embeddings to represent user preferences. Then the combination of keywords and embeddings are used as prompts to condition the generator. We optimize a weighted sum of the accuracy and preference scores so that the generated content has a good balance between them. Compared to a baseline method without personalization, PMG has a significant improvement on personalization for up to 8% in terms of LPIPS while retaining the accuracy of generation.

With the increasing availability of trajectory data, it is important to have good indexes to facilitate query processing. In this work, we propose BT-Tree, which is built through a recursive bi-partitioning approach, for the processing of range and KNN queries for past trajectory data. We first propose a cost function based method (CFBM) to build the BT-Tree. Specifically, we design a novel cost function, which incorporates the characteristics of both the data and historical query workload, to decide how to partition a BT-Tree node. Then we propose a reinforcement learning (RL) based method to address CFBM's limitations, such as making locally optimal decisions that may lead to global suboptimality. Experiments on three real datasets with up to 800 million data points show that the CFBM generally outperforms the baselines in terms of query processing time and the RL based method consistently outperforms the baselines and has more significant advantages on larger datasets.

The task of entity alignment between knowledge graphs (KGs) aims to identify every pair of entities from two different KGs that represent the same entity. Many machine learning-based methods have been proposed for this task. However, to our best knowledge, existing methods all requiremanually craftedseed alignments, which are expensive to obtain. In this paper, we propose the first fully automatic alignment method named AutoAlign, which does not require any manually crafted seed alignments. Specifically, for predicate embeddings, AutoAlign constructs a predicate-proximity-graph with the help of large language models to automatically capture the similarity between predicates across two KGs. For entity embeddings, AutoAlign first computes the entity embeddings of each KG independently using TransE, and then shifts the two KGs' entity embeddings into the same vector space by computing the similarity between entities based on their attributes. Thus, both predicate alignment and entity alignment can be done without manually crafted seed alignments. AutoAlign is not only fully automatic, but also highly effective. Experiments using real-world KGs show that AutoAlign improves the performance of entity alignment significantly compared to state-of-the-art methods. Our source code is available at ruizhang-ai/AutoAlign.

Multi-domain recommendation (MDR) aims to provide recommendations for different domains (e.g., types of products) with overlapping users/items and is common for platforms such as Amazon, Facebook, and LinkedIn that host multiple services. Existing MDR models face two challenges: First, it is difficult to disentangle knowledge that generalizes across domains (e.g., a user likes cheap items) and knowledge specific to a single domain (e.g., a user likes blue clothing but not blue cars). Second, they have limited ability to transfer knowledge across domains with small overlaps. We propose a new MDR method named EDDA with two key components, i.e., embedding disentangling recommender and domain alignment, to tackle the two challenges respectively. In particular, the embedding disentangling recommender separates both the model and embedding for the inter-domain part and the intra-domain part, while most existing MDR methods only focus on model-level disentangling. The domain alignment leverages random walks from graph processing to identify similar user/item pairs from different domains and encourages similar user/item pairs to have similar embeddings, enhancing knowledge transfer. We compare EDDA with 12 state-of-the-art baselines on 3 real datasets. The results show that EDDA consistently outperforms the baselines on all datasets and domains. All datasets and codes are available at https://github.com/Stevenn9981/EDDA.

Re-ranking, as the final stage of the multi-stage recommender systems (MRS), aims at modeling the listwise context and the cross-item interactions between the candidate items. The objective is usually the overall utility (e.g., total clicks or revenue) of the re-ranked list, which is determined not only by the relevance, but also by the diversity of the list. However, existing methods equally promote diversity for all users and often compromise the relevance ranking. In reality, users have different diversity preferences and we should diversify the list tailored to individual users’ interests and needs. Users’ behavior history contains rich information which may be used for inferring their diversity preferences, but has rarely been explored in existing work. In this work, we propose a novel neural re-ranking with personalized diversification method (dubbed RAPID) to address the above challenge. RAPID explicitly models each user’s preference distribution over different topics by exploiting the intra- and inter-topic interactions from the user’s behavior history. The personalized diversity gain brought by each candidate item is then measured by the item’s marginal diversity and the learned personalized preference. The relevance and the personalized diversity are jointly optimized in an end-to-end manner to automatically manage the relevance-diversity tradeoff. Experimental results on two public datasets and a proprietary dataset show that RAPID outperforms the state-of-the-art with the highest utility and the best relevance-diversity tradeoff. We further prove that RAPID has a regret bound of $\tilde O(\sqrt n )$ on utility, which provides theoretical guarantee that its performance is near-optimal.

Bregman distances (also known as Bregman divergences) are widely used in machine learning, speech recognition and signal processing, and kNN searches with Bregman distances have become increasingly important with the rapid advances of multimedia applications. Data in multimedia applications such as images and videos are commonly transformed into space of hundreds of dimensions. Such high-dimensional space has posed significant challenges for existing kNN search algorithms with Bregman distances, which could only handle data of medium dimensionality (typically less than 100). This paper addresses the urgent problem of high-dimensional kNN search with Bregman distances. We propose a novel partition-filter-refinement framework. Specifically, we propose an optimized dimensionality partitioning scheme to solve several non-trivial issues. First, an effective bound from each partitioned subspace to obtain exact kNN results is derived. Second, we conduct an in-depth analysis of the optimized number of partitions and devise an effective strategy for partitioning. Third, we design an efficient integrated index structure for all the subspaces together to accelerate the search processing. Moreover, we extend our exact solution to an approximate version by a trade-off between the accuracy and efficiency. Experimental results on four real-world datasets and two synthetic datasets show the clear advantage of our method in comparison to state-of-the-art algorithms.

Various types of user behaviors are recorded in most real-world recommendation scenarios. To fully utilize the multi-behavior information, the exploration of multiplex interaction among them is essential. Many multi-task learning based multi-behavior methods are proposed recently to use multiple types of supervision signals and perform information transfer among them. Despite the great successes, these methods fail to design prediction tasks comprehensively, leading to insufficient utilization of multi-behavior correlative information. Besides, these methods are either based on the weighting of expert information extracted from the coupled input or modeling of information transfer between multiple behavior levels through task-specific extractors, which are usually accompanied by negative transfer phenomenon1. To address the above problems, we propose a multi-behavior recommendation framework, called Hierarchical Projection Enhanced Multi-behavior Recommendation (HPMR). The key module, Projection-based Transfer Network (PTN), uses the projection mechanism to "explicitly" model the correlations of upstream and downstream behaviors, refines the upstream behavior representations, and fully uses the refined representations to enhance the learning of downstream tasks. Offline experiments on public and industrial datasets and online A/B test further verify the effectiveness of HPMR in modeling the associations from upstream to downstream and alleviating the negative transfer. The source code and datasets are available at https://github.com/MC-CV/HPMR.

As an emerging field driven by industrial applications, integrated re-ranking combines lists from upstream sources into a single list, and presents it to the user. The quality of integrated re-ranking is especially sensitive to real-time user behaviors and preferences. However, existing methods are all built on the cloud-to-edge framework, where mixed lists are generated by the cloud model and then sent to the devices. Despite its effectiveness, such a framework fails to capture users' real-time preferences due to the network bandwidth and latency. Hence, we propose to place the integrated re-ranking model on devices, allowing for the full exploitation of real-time behaviors. To achieve this, we need to address two key issues: first, how to extract users' preferences for different sources from heterogeneous and imbalanced user behaviors; second, how to explore the correlation between the extracted personalized preferences and the candidate items. In this work, we present the first on-Device Integrated Re-ranking framework, DIR, to avoid delays in processing real-time user behaviors. DIR includes a multi-sequence behavior modeling module to extract the user's source-level preferences, and a preference-adaptive re-ranking module to incorporate personalized source-level preferences into the re-ranking of candidate items. Besides, we design exposure loss and utility loss to jointly optimize exposure fairness and overall utility. Extensive experiments on three datasets show that DIR significantly outperforms the state-of-the-art baselines in utility-based and fairness-based metrics.

The cost of hardware and energy consumption on training a click-through rate (CTR) model is highly prohibitive. A recent promising direction for reducing such costs is data distillation with gradient matching, which aims to synthesize a small distilled dataset to guide the model to a similar parameter space as those trained on real data. However, there are two main challenges to implementing such a method in the recommendation field: (1) The categorical recommended data are high dimensional and sparse one- or multi-hot data which will block the gradient flow, causing backpropagation-based data distillation invalid. (2) The data distillation process with gradient matching is computationally expensive due to the bi-level optimization. To this end, we investigate efficient data distillation tailored for recommendation data with plenty of side information where we formulate the discrete data to the dense and continuous data format. Then, we further introduce a one-step gradient matching scheme, which performs gradient matching for only a single step to overcome the inefficient training process. The overall proposed method is called Categorical data distillation with Gradient Matching (CGM), which is capable of distilling a large dataset into a small of informative synthetic data for training CTR models from scratch. Experimental results show that our proposed method not only outperforms the state-of-the-art coreset selection and data distillation methods but also has remarkable cross-architecture performance. Moreover, we explore the application of CGM on model retraining and mitigate the effect of different random seeds on the training results.

A common practice to keep the freshness of an offline Recommender System (RS) is to train models that fit the user’s most recent behaviour while directly replacing the outdated historical model. However, many feature engineering and computing resources are used to train these historical models, but they are underutilized in the downstream RS model training. In this paper, to turn these historical models into treasures, we introduce a model inversed data synthesis framework, which can recover training data information from the historical model and use it for knowledge transfer. This framework synthesizes a new form of data from the historical model. Specifically, we ’invert’ an off-the-shield pretrained model to synthesize binary class user-item pairs beginning from random noise without requiring any additional information from the training dataset. To synthesize informative data from a pretrained model, we propose a new continuous data type rather than the original one- or multi-hot vectors. An additional statistical regularization is added to further improve the quality of the synthetic data inverted from the deep model with batch normalization. The experimental results show that our framework can generalize across different types of models. We can efficiently train different types of classical Click-Through-Rate (CTR) prediction models from scratch with significantly few inversed synthetic data (2 orders of magnitude). Moreover, our framework can also work well in the knowledge transfer scenarios such as model retraining and data-free knowledge distillation.

With the explosive growth of commercial applications of recommender systems, multi-scenario recommendation (MSR) has attracted considerable attention, which utilizes data from multiple domains to improve their recommendation performance simultaneously. However, training a unified deep recommender system (DRS) may not explicitly comprehend the commonality and difference among domains, whereas training an individual model for each domain neglects the global information and incurs high computation costs. Likewise, fine-tuning on each domain is inefficient, and recent advances that apply the prompt tuning technique to improve fine-tuning efficiency rely solely on large-sized transformers. In this work, we propose a novel prompt-enhanced paradigm for multi-scenario recommendation. Specifically, a unified DRS backbone model is first pre-trained using data from all the domains in order to capture the commonality across domains. Then, we conduct prompt tuning with two novel prompt modules, capturing the distinctions among various domains and users. Our experiments on Douban, Amazon, and Ali-CCP datasets demonstrate the effectiveness of the proposed paradigm with two noticeable strengths: (i) its great compatibility with various DRS backbone models, and (ii) its high computation and storage efficiency with only 6% trainable parameters in prompt tuning phase. The implementation code is available for easy reproduction.

Multi-layer perceptron (MLP) serves as a core component in many deep models for click-through rate (CTR) prediction. However, vanilla MLP networks are inefficient in learning multiplicative feature interactions, making feature interaction learning an essential topic for CTR prediction. Existing feature interaction networks are effective in complementing the learning of MLPs, but they often fall short of the performance of MLPs when applied alone. Thus, their integration with MLP networks is necessary to achieve improved performance. This situation motivates us to explore a better alternative to the MLP backbone that could potentially replace MLPs. Inspired by factorization machines, in this paper, we propose FINAL, a factorized interaction layer that extends the widely-used linear layer and is capable of learning 2nd-order feature interactions. Similar to MLPs, multiple FINAL layers can be stacked into a FINAL block, yielding feature interactions with an exponential degree growth. We unify feature interactions and MLPs into a single FINAL block and empirically show its effectiveness as a replacement for the MLP block. Furthermore, we explore the ensemble of two FINAL blocks as an enhanced two-stream CTR model, setting a new state-of-the-art on open benchmark datasets. FINAL can be easily adopted as a building block and has achieved business metric gains in multiple applications at Huawei. Our source code will be made available at MindSpore/models and FuxiCTR/model_zoo.

Most click models focus on user behaviors towards a single list. However, with the development of user interface (UI) design, the layout of displayed items on a result page tends to be multi-block style instead of a single list, which requires different assumptions to model user behaviors more accurately. There exist click models for multi-block pages in desktop contexts, but they cannot be directly applied to mobile scenarios due to different interaction manners, result types and especially multi-block presentation styles. In particular, multi-block mobile pages can normally be decomposed into interleavings of basic vertical blocks and horizontal blocks, thus resulting in typically F-shape forms. To mitigate gaps between desktop and mobile contexts for multi-block pages, we conduct a user eye-tracking study, and identify users' sequential browsing, block skip and comparison patterns on F-shape pages. These findings lead to the design of a novel F-shape Click Model (FSCM), which serves as a general solution to multi-block mobile pages. Firstly, we construct a Directed Acyclic Graph (DAG) for each page, where each item is regarded as a vertex and each edge indicates the user's possible examination flow. Secondly, we propose DAG-structured GRUs and a comparison module to model users' sequential (sequential browsing, block skip) and non-sequential (comparison) behaviors respectively. Finally, we combine GRU states and comparison patterns to perform user click predictions. Experiments show that FSCM outperforms baseline models.

Reranking, as the final stage of multi-stage recommender systems, refines the initial lists to maximize the total utility. With the development of multimedia and user interface design, the recommendation page has evolved to a multi-list style. Separately employing traditional list-level reranking methods for different lists overlooks the inter-list interactions and the effect of different page formats, thus yielding suboptimal reranking performance. Moreover, simply applying a shared network for all the lists fails to capture the commonalities and distinctions in user behaviors on different lists. To this end, we propose to draw a bird's-eye view of page-level reranking and design a novel Page-level Attentional Reranking (PAR) model. We introduce a hierarchical dual-side attention module to extract personalized intra- and inter-list interactions. A spatial-scaled attention network is devised to integrate the spatial relationship into pairwise item influences, which explicitly models the page format. The multi-gated mixture-of-experts module is further applied to capture the commonalities and differences of user behaviors between different lists. Extensive experiments on a public dataset and a proprietary dataset show that PAR significantly outperforms existing baseline models.

Multi-types of user behavior data (e.g., clicking, adding to cart, and purchasing) are recorded in most real-world recommendation scenarios, which can help to learn users’ multi-faceted preferences. However, it is challenging to explore multi-behavior data due to the unbalanced data distribution and sparse target behavior, which lead to the inadequate modeling of high-order relations when treating multi-behavior data “as features” and gradient conflict in multi-task learning when treating multi-behavior data “as labels”. In this paper, we propose CIGF, a Compressed Interaction Graph based Framework, to overcome the above limitations. Specifically, we design a novel Compressed Interaction Graph Convolution Network (CIGCN) to model instance-level high-order relations explicitly. To alleviate the potential gradient conflict when treating multi-behavior data “as labels”, we propose a Multi-Expert with Separate Input (MESI) network with separate input on the top of CIGCN for multi-task learning. Comprehensive experiments on three large-scale real-world datasets demonstrate the superiority of CIGF.

Explainable recommendation has recently attracted increasing attention from both academic and industry communities. Among different explainable strategies, generating natural language explanations is an important method, which can deliver more informative, flexible and readable explanations to facilitate better user decisions. Despite the effectiveness, existing models are mostly optimized based on the observed datasets, which can be skewed due to the selection or exposure bias. To alleviate this problem, in this paper, we formulate the task of explainable recommendation with a causal graph, and design a causality enhanced framework to generate unbiased explanations. More specifically, we firstly define an ideal unbiased learning objective, and then derive a tractable loss for the observational data based on the inverse propensity score (IPS), where the key is a sample re-weighting strategy for equalizing the loss and ideal objective in expectation. Considering that the IPS estimated from the sparse and noisy recommendation datasets can be inaccurate, we introduce a fault tolerant mechanism by minimizing the maximum loss induced by the sample weights near the IPS. For more comprehensive modeling, we further analyze and infer the potential latent confounders induced by the complex and diverse user personalities. We conduct extensive experiments by comparing with the state-of-the-art methods based on three real-world datasets to demonstrate the effectiveness of our method.

We study neural data-to-text generation to generate a sentence to describe a target entity based on its attributes. Specifically, we address two problems of the encoder-decoder framework for data-to-text generation: i) how to encode a non-linear input (e.g., a set of attributes); and ii) how to order the attributes in the generated description. Existing studies focus on the encoding problem but do not address the ordering problem, i.e., they learn the content-planning implicitly. The other approaches focus on two-stage models but overlook the encoding problem. To address the two problems at once, we propose a model namedTransCPto explicitly learn content-planning and integrate them into a description generation model in an end-to-end fashion. We propose a novel Transformer-based Pointer Network withgated residual attentionandimportance maskingto learn a content-plan. To integrate the content-plan with a description generator, we propose a tracking mechanism to trace the extent to which the content-plan is exposed in the previous decoding time-step. This helps the description generator select the attributes to be mentioned in proper order. Experimental results show that our model consistently outperforms state-of-the-art baselines by up to 2% and 3% in terms of BLEU score on two real-world datasets.

Region similarity learning plays an essential role in applications such as business site selection, region recommendation, and urban planning. Earlier studies mainly represent regions as bags of points of interest (POIs) for region similarity comparisons, which cannot fully exploit the spatial features of the regions. Recently, researchers propose to use deep neural networks to exploit spatial features such as POI geo-coordinates and categories, which have produced more accurate and robust region similarity learning results. However, many useful features such as the height and size of a POI, and the distance and relative importance between the POIs, are still overlooked in these methods. To take advantage of such features, we propose to represent regions as graphs, where nodes are POIs with rich features such as height, size, and hexagonal coordinates, while edges are the relationships between POIs formulated by their road network distances. To capture POIs’ importance, we weigh them by their height and size. Since there is limited availability of ground-truth region similarity data, we propose a contrastive learning-based multi-relational graph neural network (C-MPGCN) for region similarity learning based on the graph representations. To generate data for model training, we propose a soft graph edit distance (SGED) based algorithm to generate triples of similar and dissimilar graphs of a given graph (representing a given region) based on the POI weights. Experimental results show that C-MPGCN outperforms the state-of-the-art methods for region similarity learning consistently with an improvement of at least 8.6% and 9.4% in terms of MRR and HR@1, respectively.

Debiased recommendation with a randomized dataset has shown very promising results in mitigating system-induced biases. However, it still lacks more theoretical insights or an ideal optimization objective function compared with the other more well-studied routes without a randomized dataset. To bridge this gap, we study the debiasing problem from a new perspective and propose to directly minimize the upper bound of an ideal objective function, which facilitates a better potential solution to system-induced biases. First, we formulate a new ideal optimization objective function with a randomized dataset. Second, according to the prior constraints that an adopted loss function may satisfy, we derive two different upper bounds of the objective function: a generalization error bound with triangle inequality and a generalization error bound with separability. Third, we show that most existing related methods can be regarded as the insufficient optimization of these two upper bounds. Fourth, we propose a novel method called debiasing approximate upper bound ( DUB ) with a randomized dataset, which achieves a more sufficient optimization of these upper bounds. Finally, we conduct extensive experiments on a public dataset and a real product dataset to verify the effectiveness of our DUB.

Numerical features (e.g., statistical features) are widely used in recommender systems and online advertising. Existing approaches for numerical feature representation in industry are primarily based on discretization. However, hard-discretization based methods (e.g., Equal Distance Discretization) are deficient in continuity while soft-discretization based methods (e.g., AutoDis) lack discriminability. To emphasize both continuity and discriminability for numerical features, we propose an end-to-end representation learning framework named NaryDis. Specifically, NaryDis first leverages hybrid n-ary encoding as an automatic discretization module to generate hybrid-grained discretization results (multiple encoded sequences). Each position of the encoded sequence is assigned with a positional embedding and an intra-ary attention network is leveraged to aggregate the positional embeddings for obtaining ary-wise representations. Then an inter-ary attention is adopted to assemble these representations, which are further constrained by a self-supervised regularization module. Comprehensive experiments on two public datasets are conducted to show the superiority and compatibility of NaryDis. Besides, we deeply investigate the properties of continuity and discriminability. Moreover, we further verify the effectiveness of NaryDis on a large-scale industrial advertisement dataset.

Music recommendation is usually modeled as a Click-Through Rate (CTR) prediction problem, which estimates the probability of a user listening a recommended song. CTR prediction can be formulated as a binary classification problem where the played songs are labeled as positive samples and the skipped songs are labeled as negative samples. However, such naively defined labels are noisy and biased in practice, causing inaccurate model predictions. In this work, we first identify serious label noise issues in an industrial music App, and then propose an adaptive Label Correction method for Denoising (LCD) music recommendation by ensembling the noisy labels and the model outputs to encourage a consensus prediction. Extensive offline experiments are conducted to evaluate the effectiveness of LCD on both industrial and public datasets. Furthermore, in a one-week online AB test, LCD also significantly increases both the music play count and time per user by 1% to 5%.

CTR prediction is essential for modern recommender systems. Ranging from early factorization machines to deep learning based models in recent years, existing CTR methods focus on capturing useful feature interactions or mining important behavior patterns. Despite the effectiveness, we argue that these methods suffer from the risk of label sparsity (i.e., the user-item interactions are highly sparse with respect to the feature space), label noise (i.e., the collected user-item interactions are usually noisy), and the underuse of domain knowledge (i.e., the pairwise correlations between samples). To address these challenging problems, we propose a novel Multi-Interest Self-Supervised learning (MISS) framework which enhances the feature embeddings with interest-level self-supervision signals. With the help of two novel CNN-based multi-interest extractors, self-supervision signals are discovered with full considerations of different interest representations (point-wise and union-wise), interest dependencies (short-range and long-range), and interest correlations (inter-item and intra-item). Based on that, contrastive learning losses are further applied to the augmented views of interest representations, which effectively improves the feature representation learning. Furthermore, our proposed MISS frame-work can be used as an “plug-in” component with existing CTR prediction models and further boost their performances. Extensive experiments on three large-scale datasets show that MISS significantly outperforms the state-of-the-art models, by up to 13.55% in AUC, and also enjoys good compatibility with representative deep CTR models.

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.

Online education, which educates students that cannot be present at school, has become an important supplement to traditional education. Without the direct supervision and instruction of teachers, online education is always concerned with potential distractions and misunderstandings. Learning Style Classification (LSC) is proposed to analyze the learning behavior patterns of online learning users, based on which personalized learning paths are generated to help them learn and maintain their interests.

Post-click conversion rate (CVR) prediction is an essential task for discovering user interests and increasing platform revenues in a range of industrial applications. One of the most challenging problems of this task is the existence of severe selection bias caused by the inherent self-selection behavior of users and the item selection process of systems. Currently, doubly robust (DR) learning approaches achieve the state-of-the-art performance for debiasing CVR prediction. However, in this paper, by theoretically analyzing the bias, variance and generalization bounds of DR methods, we find that existing DR approaches may have poor generalization caused by inaccurate estimation of propensity scores and imputation errors, which often occur in practice. Motivated by such analysis, we propose a generalized learning framework that not only unifies existing DR methods, but also provides a valuable opportunity to develop a series of new debiasing techniques to accommodate different application scenarios. Based on the framework, we propose two new DR methods, namely DR-BIAS and DR-MSE. DR-BIAS directly controls the bias of DR loss, while DR-MSE balances the bias and variance flexibly, which achieves better generalization performance. In addition, we propose a novel tri-level joint learning optimization method for DR-MSE in CVR prediction, and an efficient training algorithm correspondingly. We conduct extensive experiments on both real-world and semi-synthetic datasets, which validate the effectiveness of our proposed methods.

Detecting beneficial feature interactions is essential in recommender systems, and existing approaches achieve this by examining all the possible feature interactions. However, the cost of examining all the possible higher-order feature interactions is prohibitive (exponentially growing with the order increasing). Hence existing approaches only detect limited order (e.g., combinations of up to four features) beneficial feature interactions, which may miss beneficial feature interactions with orders higher than the limitation. In this paper, we propose a hypergraph neural network based model named HIRS. HIRS is the first work that directly generates beneficial feature interactions of arbitrary orders and makes recommendation predictions accordingly. The number of generated feature interactions can be specified to be much smaller than the number of all the possible interactions and hence, our model admits a much lower running time. To achieve an effective algorithm, we exploit three properties of beneficial feature interactions, and propose deep-infomax-based methods to guide the interaction generation. Our experimental results show that HIRS outperforms state-of-the-art algorithms by up to 5% in terms of recommendation accuracy.

Deep learning-based recommendation has become a widely adopted technique in various online applications. Typically, a deployed model undergoes frequent re-training to capture users' dynamic behaviors from newly collected interaction logs. However, the current model training process only acquires users' feedbacks as labels, but fails to take into account the errors made in previous recommendations. Inspired by the intuition that humans usually reflect and learn from mistakes, in this paper, we attempt to build a self-correction continual learning loop (dubbed ReLoop) for recommender systems. In particular, a new customized loss is employed to encourage every new model version to reduce prediction errors over the previous model version during training. Our ReLoop learning framework enables a continual self-correction process in the long run and thus is expected to obtain better performance over existing training strategies. Both offline experiments and an online A/B test have been conducted to validate the effectiveness of ReLoop.

Building a multi-stage cascade ranking system is a commonly used solution to balance the efficiency and effectiveness in modern information retrieval (IR) applications, such as recommendation and web search. Despite the popularity in practice, the literature specific on multi-stage cascade ranking systems is relatively scarce. The common practice is to train rankers of each stage independently using the same user feedback data (a.k.a., impression data), disregarding the data flow and the possible interactions between stages. This straightforward solution could lead to a sub-optimal system because of the sample selection bias (SSB) issue, which is especially damaging for cascade rankers due to the negative effect accumulated in the multiple stages. Worse still, the interactions between the rankers of each stage are not fully exploited. This paper provides an elaborate analysis of this commonly used solution to reveal its limitations. By studying the essence of cascade ranking, we propose a joint training framework named RankFlow to alleviate the SSB issue and exploit the interactions between the cascade rankers, which is the first systematic solution for this topic. We propose a paradigm of training cascade rankers that emphasizes the importance of fitting rankers on stage-specific data distributions instead of the unified user feedback distribution. We design the RankFlow framework based on this paradigm: The training data of each stage is generated by its preceding stages while the guidance signals not only come from the logs but its successors. Extensive experiments are conducted on various IR scenarios, including recommendation, web search and advertisement. The results verify the efficacy and superiority of RankFlow.

As the final stage of the multi-stage recommender system (MRS), reranking directly affects users' experience and satisfaction, thus playing a critical role in MRS. Despite the improvement achieved in the existing work, three issues are yet to be solved. First, users' historical behaviors contain rich preference information, such as users' long and short-term interests, but are not fully exploited in reranking. Previous work typically treats items in history equally important, neglecting the dynamic interaction between the history and candidate items. Second, existing reranking models focus on learning interactions at the item level while ignoring the fine-grained feature-level interactions. Lastly, estimating the reranking score on the ordered initial list before reranking may lead to the early scoring problem, thereby yielding suboptimal reranking performance. To address the above issues, we propose a framework named Multi-level Interaction Reranking (MIR). MIR combines low-level cross-item interaction and high-level set-to-list interaction, where we view the candidate items to be reranked as a set and the users' behavior history in chronological order as a list. We design a novel SLAttention structure for modeling the set-to-list interactions with personalized long-short term interests. Moreover, feature-level interactions are incorporated to capture the fine-grained influence among items. We design MIR in such a way that any permutation of the input items would not change the output ranking, and we theoretically prove it. Extensive experiments on three public and proprietary datasets show that MIR significantly outperforms the state-of-the-art models using various ranking and utility metrics.

The past two decades have witnessed the rapid development of personalized recommendation techniques. Despite the significant progress made in both research and practice of recommender systems, to date, there is a lack of a widely-recognized benchmarking standard in this field. Many of the existing studies perform model evaluations and comparisons in an ad-hoc manner, for example, by employing their own private data splits or using a different experimental setting. However, such conventions not only increase the difficulty in reproducing existing studies, but also lead to inconsistent experimental results among them. This largely limits the credibility and practical value of research results in this field. To tackle these issues, we present an initiative project aimed for open benchmarking for recommender systems. In contrast to some earlier attempts towards this goal, we take one further step by setting up a standardized benchmarking pipeline for reproducible research, which integrates all the details about datasets, source code, hyper-parameter settings, running logs, and evaluation results. The benchmark is designed with comprehensiveness and sustainability in mind. It spans both matching and ranking tasks, and also allows anyone to easily follow and contribute. We believe that our benchmark could not only reduce the redundant efforts of researchers to re-implement or re-run existing baselines, but also drive more solid and reproducible research on recommender systems.

Self-supervised learning, especially contrastive learning, has made an outstanding contribution to the development of many deep learning research fields. Recently, researchers in the acoustic signal processing field noticed its success and leveraged contrastive learning for better music representation. Typically, existing approaches maximize the similarity between two distorted audio segments sampled from the same music. In other words, they ensure a semantic agreement at the music level. However, those coarse-grained methods neglect some inessential or noisy elements at the frame level, which may be detrimental to the model to learn the effective representation of music. Towards this end, this paper proposes a novel Positive-nEgative frame mask for Music Representation based on the contrastive learning framework, abbreviated as PEMR. Concretely, PEMR incorporates a Positive-Negative Mask Generation module, which leverages transformer blocks to generate frame masks on Log-Mel spectrogram. We can generate self-augmented negative and positive samples by masking important components or inessential components, respectively. We devise a novel contrastive learning objective to accommodate both self-augmented positives/negatives sampled from the same music. We conduct experiments on four public datasets. The experimental results of two music-related downstream tasks, music classification and cover song identification, demonstrate the generalization ability and transferability of music representation learned by PEMR.

The advent of online applications such as social networks has led to an unprecedented scale of data and complex relationships among data. Hypergraphs are introduced to represent complex relationships that may involve more than two entities. A hypergraph is a generalized form of a graph, where edges are generalized to hyperedges. Each hyperedge may consist of any number of vertices. The flexibility of hyperedges also brings challenges in distributed hypergraph processing. In particular, a hypergraph is more difficult to be partitioned and distributed among$k$workers with balanced partitions. In this paper, we propose to convert a hypergraph into an intersection graph before partitioning by leveraging the inherent shared relationships among hypergraphs. We explore the intersection graph construction method and the corresponding partition strategy which can achieve the goal of evenly distributing vertices and hyperedges across workers, while yielding a significant communication reduction. We also design a distributed processing framework named$Hyraph$that can directly run hypergraph analysis algorithms on our intersection graphs. Experimental results on real datasets confirm the effectiveness of our techniques and the efficiency of the$Hyraph$framework.

Bregman distances (also known as Bregman divergences) are widely used in machine learning, speech recognition and signal processing, andkNN searches with Bregman distances have become increasingly important with the rapid advances of multimedia applications. Data in multimedia applications such as images and videos are commonly transformed into space of hundreds of dimensions. Such high-dimensional space has posed significant challenges for existingkNN search algorithms with Bregman distances, which could only handle data of medium dimensionality (typically less than 100). This paper addresses the urgent problem of high-dimensionalkNN search with Bregman distances. We propose a novel partition-filter-refinement framework. Specifically, we propose an optimized dimensionality partitioning scheme to solve several non-trivial issues. First, an effective bound from each partitioned subspace to obtain exactkNN results is derived. Second, we conduct an in-depth analysis of the optimized number of partitions and devise an effective strategy for partitioning. Third, we design an efficient integrated index structure for all the subspaces together to accelerate the search processing. Moreover, we extend our exact solution to an approximate version by a trade-off between the accuracy and efficiency. Experimental results on four real-world datasets and two synthetic datasets show the clear advantage of our method in comparison to state-of-the-art algorithms.

We introduce the task of webpage briefing (WB) to provide a summary of a webpage in a hierarchical manner, from the broad topic of the webpage, to finer level key attributes. A straightforward approach for this task is to train a machine learning model for generating topics and extracting key attributes. However, such a model may not perform well on webpages that are from domains not seen in the training data. An ideal model should be able to adapt to unseen domains while preserving knowledge learned from the seen domains. Knowledge distillation (KD) offers a potential solution, in which a teacher pre-trained with specific domains can pass the knowledge to a student, while unseen domains can also be added to increase the robustness of the models. However, existing works usually assume the models have no access to seen domains during distillation and the knowledge on seen domains may be lost. In our setting, we have access to the generated topics, which contain representative knowledge of seen domains and can help preserve that knowledge during distillation. Moreover, a vanilla KD does not pass on the knowledge about the location patterns of the informative contents in webpages, which are essential for identifying the topics to be generated or the key attributes to be extracted. To preserve more knowledge of seen domains and to better utilize the location patterns, we propose a Dual Distillation model which consists of identification distillation (ID) and understanding distillation (UD); ID distills knowledge on the identification of informative contents under the guidance of the learned topics of seen domains, while UD distills knowledge on topic generation or key attribute extraction. Since topics and key attributes are distilled separately in two students in Dual Distillation, the inherent correlations between them are not utilized. To better exploit such correlations, we propose a Triple Distillation model which consists of a shared ID and two UDs, one for topic generation and the other for key attribute extraction. We further propose a joint model for WB with signal enhancement and exchange among a key attribute extractor, a topic generator, and an informative section predictor. Experiments on real-world webpages show that our models achieve high performances for WB, and validate the superiority of Dual Distillation and Triple Distillation in their target settings. Experiments also show that the proposed joint model outperforms single-task baselines and other joint models.

Due to the wide applications in recommendation systems, multi-class label prediction and deep learning, the Maximum Inner Product (MIP) search problem has received extensive attention in recent years. Faced with large-scale datasets containing high-dimensional feature vectors, the state-of-the-art LSH-based methods usually require a large number of hash tables or long hash codes to ensure the searching quality, which takes up lots of index space and causes excessive disk page accesses. In this paper, we relax the guarantee of accuracy for efficiency and propose an efficient method for c-Approximate Maximum Inner Product (c-AMIP) search with a lightweight iDistance index. We project high-dimensional points to low-dimensional ones via 2-stable random projections and derive probability-guaranteed searching conditions, by which the c-AMIP results can be guaranteed in accuracy with arbitrary probabilities. To further improve the efficiency, we propose Quick-Probe for quickly determining the searching bound satisfying the derived condition in advance, avoiding the inefficient incremental searching process. Extensive experimental evaluations on four real datasets demonstrate that our method requires less pre-processing cost including index size and pre-processing time. In addition, compared to the state-of-the-art benchmark methods, it provides superior results on searching quality in terms of overall ratio and recall, and efficiency in terms of page access and running time.

User and item attributes are essential side-information; their interactions (i.e., their co-occurrence in the sample data) can significantly enhance prediction accuracy in various recommender systems. We identify two different types of attribute interactions, inner interactions and cross interactions: inner interactions are those between only user attributes or those between only item attributes; cross interactions are those between user attributes and item attributes. Existing models do not distinguish these two types of attribute interactions, which may not be the most effective way to exploit the information carried by the interactions. To address this drawback, we propose a neural Graph Matching based Collaborative Filtering model (GMCF), which effectively captures the two types of attribute interactions through modeling and aggregating attribute interactions in a graph matching structure for recommendation. In our model, the two essential recommendation procedures, characteristic learning and preference matching, are explicitly conducted through graph learning (based on inner interactions) and node matching (based on cross interactions), respectively. Experimental results show that our model outperforms state-of-the-art models. Further studies verify the effectiveness of GMCF in improving the accuracy of recommendation.

Graph structural information such as topologies or connectivities provides valuable guidance for graph convolutional networks (GCNs) to learn nodes' representations. Existing GCN models that capture nodes' structural information weight in- and out-neighbors equally or differentiate in- and out-neighbors globally without considering nodes' local topologies. We observe that in- and out-neighbors contribute differently for nodes with different local topologies. To explore the directional structural information for different nodes, we propose a GCN model with weighted structural features, named WGCN. WGCN first captures nodes' structural fingerprints via a direction and degree aware Random Walk with Restart algorithm, where the walk is guided by both edge direction and nodes' in- and out-degrees. Then, the interactions between nodes' structural fingerprints are used as the weighted node structural features. To further capture nodes' high-order dependencies and graph geometry, WGCN embeds graphs into a latent space to obtain nodes' latent neighbors and geometrical relationships. Based on nodes' geometrical relationships in the latent space, WGCN differentiates latent, in-, and out-neighbors with an attention-based geometrical aggregation. Experiments on transductive node classification tasks show that WGCN outperforms the baseline models consistently by up to 17.07% in terms of accuracy on five benchmark datasets.

Selectivity estimation aims at estimating the number of database objects that satisfy a selection criterion. Answering this problem accurately and efficiently is essential to many applications, such as density estimation, outlier detection, query optimization, and data integration. The estimation problem is especially challenging for large-scale high-dimensional data due to the curse of dimensionality, the large variance of selectivity across different queries, and the need to make the estimator consistent (i.e., the selectivity is non-decreasing in the threshold). We propose a new deep learning-based model that learns a query-dependent piecewise linear function as selectivity estimator, which is flexible to fit the selectivity curve of any distance function and query object, while guaranteeing that the output is non-decreasing in the threshold. To improve the accuracy for large datasets, we propose to partition the dataset into multiple disjoint subsets and build a local model on each of them. We perform experiments on real datasets and show that the proposed model consistently outperforms state-of-the-art models in accuracy in an efficient way and is useful for real applications.

Personalized PageRank (PPR) is a critical measure of the importance of a node t to a source node s in a graph. The Single-Source PPR (SSPPR) query computes the PPR's of all the nodes with respect to s on a directed graph G with n nodes and m edges; and it is an essential operation widely used in graph applications. In this paper, we propose novel algorithms for answering two variants of SSPPR queries: (i) high-precision queries and (ii) approximate queries.

Recommendation datasets are prone to selection biases due to self-selection behavior of users and item selection process of systems. This makes explicitly combating selection biases an essential problem in training recommender systems. Most previous studies assume no unbiased data available for training. We relax this assumption and assume that a small subset of training data is unbiased. Then, we propose a novel objective that utilizes the unbiased data to adaptively assign propensity weights to biased training ratings. This objective, combined with unbiased performance estimators, alleviates the effects of selection biases on the training of recommender systems. To optimize the objective, we propose an efficient algorithm that minimizes the variance of propensity estimates for better generalized recommender systems. Extensive experiments on two real-world datasets confirm the advantages of our approach in significantly reducing both the error of rating prediction and the variance of propensity estimation.

Shortest-path distances on road networks have many applications such as finding nearest places of interest (POI) for travel recommendations. To compute a shortest-path distance, traditional approaches traverse the road network to find the shortest path and return the path length. When the distances are needed first (e.g., to rank POIs) while the shortest paths may be computed later (e.g., after a POI is chosen), one may precompute and store the distances, and answer distance queries by simple lookups. This approach, however, falls short in the worst-cast space cost – O(n2) for n vertices even with various optimizations. To address these limitations, we propose to learn an embedding for every vertex that preserves its distances to the other vertices. We then train a multi-layer perceptron (MLP) to predict the distance between two vertices given their embeddings. We thus achieve fast distance predictions without a high space cost. Experimental results on real road networks confirm these advantages. Meanwhile, our approach is up to 97% more accurate than the state-of-the-art approaches for distance predictions.

Hexagonal CNN models have shown superior performance in applications such as IACT data analysis and aerial scene classification due to their better rotation symmetry and reduced anisotropy. In order to realize hexagonal processing, existing studies mainly use the ZeroOut method to imitate hexagonal processing, which causes substantial memory and computation overheads. We address this deficiency with a novel native hexagonal CNN framework named HexCNN. HexCNN takes hexagon-shaped input and performs forward and backward propagation on the original form of the input based on hexagon-shaped filters, hence avoiding computation and memory overheads caused by imitation. For applications with rectangle-shaped input but require hexagonal processing, HexCNN can be applied by padding the input into hexagon-shape as preprocessing. In this case, we show that the time and space efficiency of HexCNN still outperforms existing hexagonal CNN methods substantially. Experimental results show that compared with the state-of-the-art models, which imitate hexagonal processing but using rectangle-shaped filters, HexCNN reduces the training time by up to 42.2%. Meanwhile, HexCNN saves the memory space cost by up to 25% and 41.7% for loading the input and performing convolution, respectively.

Inspired by the great success of machine learning in the past decade, people have been thinking about the possibility of improving the theoretical results by exploring data distribution. In this paper, we revisit a fundamental problem called Distributed Tracking (DT) under an assumption that the data follows a certain (known or unknown) distribution, and propose a number Data-dependent algorithms with improved theoretical bounds. Informally, in the DT problem, there is a coordinator and k players, where the coordinator holds a threshold N and each player has a counter. At each time stamp, at most one counter can be increased by one. The job of the coordinator is to capture the exact moment when the sum of all these k counters reaches N. The goal is to minimise the communication cost. While our first type of algorithms assume the concrete data distribution is known in advance, our second type of algorithms can learn the distribution on the fly. Both of the algorithms achieve a communication cost bounded by O(k log log N) with high probability, improving the state-of-the-art data-independent bound O(k log N/k). We further propose a number of implementation optimisation heuristics to improve both efficiency and robustness of the algorithms. Finally, we conduct extensive experiments on three real datasets and four synthetic datasets. The experimental results show that the communication cost of our algorithms is as least as $20%$ of that of the state-of-the-art algorithms.

Academic homepages are an important source for learning researchers' profiles. Recognising person names and publications in academic homepages are two fundamental tasks for understanding the identities of the homepages and collaboration networks of the researchers. Existing studies have tackled person name recognition and publication recognition separately. We observe that these two tasks are correlated since person names and publications often co-occur. Further, there are strong position patterns for the occurrence of person names and publications. With these observations, we propose a novel deep learning model consisting of two main modules, an alternatingly updated memory module which exploits the knowledge and correlation from both tasks, and a position-aware memory module which captures the patterns of where in a homepage names and publications appear. Empirical results show that our proposed model outperforms the state-of-the-art publication recognition model by 3.64% in F1 score and outperforms the state-of-the-art person name recognition model by 2.06% in F1 score. Ablation studies and visualisation confirm the effectiveness of the proposed modules.

The massive amount of data and large variety of data distributions in the big data era call for access methods that are efficient in both query processing and index management, and over both practical and worst-case workloads. To address this need, we revisit two classic multidimensional access methods—the R-tree and the space-filling curve. We propose a novel R-tree packing strategy based on space-filling curves. This strategy produces R-trees with an asymptotically optimal I/O complexity for window queries in the worst case. Experiments show that our R-trees are highly efficient in querying both real and synthetic data of different distributions. The proposed strategy is also simple to parallelize, since it relies only on sorting. We propose a parallel algorithm for R-tree bulk-loading based on the proposed packing strategy and analyze its performance under the massively parallel communication model. To handle dynamic data updates, we further propose index update algorithms that process data insertions and deletions without compromising the optimal query I/O complexity. Experimental results confirm the effectiveness and efficiency of the proposed R-tree bulk-loading and updating algorithms over large data sets.

DBSCAN is a popular clustering algorithm that can discover clusters of arbitrary shapes with broad applications. However, DBSCAN is computationally expensive, as it performs range queries for all the points to determine their neighbors and grow the clusters. To address this problem, we propose a novel approximate density-based clustering algorithm named DBSVEC. DBSVEC introduces support vectors into density-based clustering, which allows performing range queries only on a small subset of points called the core support vectors. This technique significantly improves the efficiency while retaining high-quality cluster results. We evaluate the performance of DBSVEC via extensive experiments on real and synthetic datasets. The results show that DBSVEC is up to three orders of magnitude faster than DBSCAN. Compared with the state-of-the-art approximate density-based clustering methods, DBSVEC is up to two orders of magnitude faster, and the clustering results of DBSVEC are more similar to those of DBSCAN.

Entity extraction is fundamental to many text mining tasks such as organisation name recognition. A popular approach to entity extraction is based on string matching against a dictionary of known entities. For approximate entity extraction from free text, considering solely character-based or solely token-based similarity cannot simultaneously deal with minor name variations at token-level and typos at character-level. Moreover, the tolerance of mismatch in character-level may be different from that in token-level, and the tolerance thresholds of the two levels should be able to be customised individually. In this paper, we propose an efficient character-level and token-level edit-distance based algorithm called FuzzyED. To improve the efficiency of FuzzyED, we develop various novel techniques including (i) a spanning-based candidate sub-string producing technique, (ii) a lower bound dissimilarity to determine the boundaries of candidate sub-strings, (iii) a core token based technique that makes use of the importance of tokens to reduce the number of unpromising candidate sub-strings, and (iv) a shrinking technique to reuse computation. Empirical results on real world datasets show that FuzzyED can efficiently extract entities and produce a high F1score in the range of [0.91, 0.97].

Next item recommendation is an important yet challenging task in real-world applications such as E-commerce. Since people often carry out a series of online shopping activities, in order to predict what a user may purchase next, it is essential to model the user's general taste as well as the sequential correlation between purchases. Existing models combine these two factors directly without considering the dynamic changes of a user's long-term and short-term preferences. Meanwhile, when a purchase session contains multiple items, not all of them have the same impact on the next item to purchase. To address these limitations, we propose a model that introduces hierarchical attention to dynamically balance between general taste (long-term preference) and sequential behavior (short-term preference). To weight individual items in the same session, we design a neural memory network with attention mechanism to learn the dynamic weights. Our model can adapt the embedding of each session as well as the embedding of long-term and short-term preferences. Extensive experiments on three real-world datasets show that our model significantly outperforms state-of-the-art methods based on commonly used evaluation metrics.

Building height estimation is important in many applications such as 3D city reconstruction, urban planning, and navigation. Recently, a new building height estimation method using street scene images and 2D maps was proposed. This method is more scalable than traditional methods that use high-resolution optical data, LiDAR data, or RADAR data which are expensive to obtain. The method needs to detect building rooflines and then compute building height via the pinhole camera model. We observe that this method has limitations in handling complex street scene images in which buildings overlap with each other and the rooflines are difficult to locate. We propose CBHE, a building height estimation algorithm considering both building corners and rooflines. CBHE first obtains building corner and roofline candidates in street scene images based on building footprints from 2D maps and the camera parameters. Then, we use a deep neural network named BuildingNet to classify and filter corner and roofline candidates. Based on the valid corners and rooflines from BuildingNet, CBHE computes building height via the pinhole camera model. Experimental results show that the proposed BuildingNet yields a higher accuracy on building corner and roofline candidate filtering compared with the state-of-the-art open set classifiers. Meanwhile, CBHE outperforms the baseline algorithm by over 10% in building height estimation accuracy.

Hypergraphs are generalizations of graphs where the (hyper)edges can connect any number of vertices. They are powerful tools for representing complex and non-pairwise relationships. However, existing graph computation frameworks cannot accommodate hypergraphs without converting them into graphs, because they do not offer APIs that support (hyper)edges directly. This graph conversion may create excessive replicas and result in very large graphs, causing difficulties in workload balancing. A few tools have been developed for hypergraph partitioning, but they are not general-purpose frameworks for hypergraph processing. In this paper, we propose HyperX, a general-purpose distributed hypergraph processing framework built on top of Spark. HyperX is based on the computation paradigm “Pregel”, which is user-friendly and has been widely adopted by popular graph computation frameworks. To help create balanced workloads for distributed hypergraph processing, we further investigate the hypergraph partitioning problem and propose a novel label propagation partitioning (LPP) algorithm. We conduct extensive experiments using both real and synthetic data. The result shows that HyperX achieves an order of magnitude improvement for running hypergraph learning algorithms compared with graph conversion based approaches in terms of running time, network communication costs, and memory consumption. For hypergraph partitioning, LPP outperforms the baseline algorithms significantly in these measures as well.

Microscopic traffic simulators play a major role to carry research on transportation problems. Microscopic traffic simulation is powerful because it enables efficient analysis of complex traffic problems to the highest level of detail. We developed Scalable Microscopic Adaptive Road Traffic Simulator (SMARTS) [14] that can perform large-scale simulations at a high speed by utilizing distributed computing resources. Previous results show that SMARTS can run 1.14 times faster than real time when simulating one million vehicles for the city of Melbourne on 30 distributed processors, while producing highly accurate simulation results. SMARTS' pluggable architecture allows it to be easily extended to simulate specific scenarios of interest to users. In this demonstration we show how SMARTS can be used to simulate an intersection design, the P-turn, in a major intersection of Melbourne. Our simulation shows the impact of the design on the traffic flow, confirming the justification for introduction of the particular intersection. The demo can be used as a template for future use of the simulator for other traffic problems.

We study the problem of continuous maintenance of range sum heat maps over dynamically updating data objects. The range sum (RS) here refers to the sum of the weights of the data objects enclosed by a given range (rectangle) R. Range sum problems are useful in spatio-temporal data analytics and decision making processes. Recent studies on range sum problems focus on computing the MaxRS query, which finds a location to place a rectangle R such that its RS is maximized. In real applications, knowing only the location with the maximum RS may be insufficient, because decision making is a multi-factor process where maximizing the RS may just be one of the factors. It is also important to gain an overview of the RS distribution at different locations, so that decisions can be made based on global knowledge. We therefore propose to compute a range-sum heat map that visualizes the RS value for every location in a data space. Considering that data objects may be inserted into or removed from the data space dynamically, we further study the continuous maintenance of range-sum heat maps over dynamically updating data objects. We adapt algorithms to compute range-sum heat maps and to perform heat map updates. We build a demo system to showcase the usefulness of range sum heat maps and the effectiveness of the adapted algorithms.

This paper studies the location-based web search and aims to build a unified processing paradigm for two purposes: (1) efficiently support each of the various types of location-based queries (kNN query, top-k spatial-textual query, etc.) on two major forms of geo-tagged data, i.e., spatial point data such as geo-tagged web documents, and spatial trajectory data such as a sequence of geo-tagged travel blogs by a user; (2) support interactive search to provide quick response for a query session, within which a user usually keeps refining her query by either issuing different query types or specifying different constraints (e.g., adding a keyword and/or location, changing the choice of k, etc.) until she finds the desired results. To achieve this goal, we first propose a general Top-k query called Monotone Aggregate Spatial Keyword query-MASK, which is able to cover most types of location-based web search. Next, we develop a unified indexing (called Textual-Grid-Point Inverted Index) and query processing paradigm (called ETAIL Algorithm) to answer a single MASK query efficiently. Furthermore, we extend ETAIL to provide interactive search for multiple queries within one query session, by exploiting the commonality of textual and/or spatial dimension among queries. Last, extensive experiments on four real datasets verify the robustness and efficiency of our approach.

The massive amount of data and large variety of data distributions in the big data era call for access methods that are efficient in both query processing and index bulk-loading, and over both practical and worst-case workloads. To address this need, we revisit a classic multidimensional access method - the R-tree. We propose a novel R-tree packing strategy that produces R-trees with an asymptotically optimal I/O complexity for window queries in the worst case. Our experiments show that the R-trees produced by the proposed strategy are highly efficient on real and synthetic data of different distributions. The proposed strategy is also simple to parallelize, since it relies only on sorting. We propose a parallel algorithm for R-tree bulk-loading based on the proposed packing strategy, and analyze its performance under the massively parallel communication model. Experimental results confirm the efficiency and scalability of the parallel algorithm over large data sets.

Search result diversification aims at returning diversified document lists to cover different user intents of a query. Existing diversity measures assume that the intents of a query are disjoint, and do not consider their relationships. In this paper, we introduce intent hierarchies to model the relationships between intents, and present four weighing schemes. Based on intent hierarchies, we propose several hierarchical measures that take into account the relationships between intents. We demonstrate the feasibility of hierarchical measures by using a new test collection based on TREC Web Track 2009-2013 diversity test collections and by using NTCIR-11 IMine test collection. Our main experimental findings are: (1) Hierarchical measures are more discriminative and intuitive than existing measures. In terms of intuitiveness, it is preferable for hierarchical measures to use the whole intent hierarchies than to use only the leaf nodes. (2) The types of intent hierarchies used affect the discriminative power and intuitiveness of hierarchical measures. We suggest the best type of intent hierarchies to be used according to whether the nonuniform weights are available. (3) To measure the benefits of the diversification algorithms which use automatically mined hierarchical intents, it is important to use hierarchical measures instead of existing measures.

We study result diversification in continuous spatial query processing and formulate a new type of queries, the moving k diversified nearest neighbor query (MkDNN). Given a moving query object, an MkDNN query maintains continuously the k diversified nearest neighbors of the query object. Here, how diversified the nearest neighbors are is defined on the distance between the nearest neighbors. We propose an algorithm to maintain incrementally the k diversified nearest neighbors to reduce the costs of continuous query processing. We further propose two approximate algorithms to obtain even higher query efficiency with precision bounds. We verify the effectiveness and efficiency of the proposed algorithms empirically. The results confirm the superiority of the proposed algorithms.

Microscopic traffic simulators are important tools for studying transportation systems as they describe the evolution of traffic to the highest level of detail. A major challenge to microscopic simulators is the slow simulation speed due to the complexity of traffic models. We have developed the Scalable Microscopic Adaptive Road Traffic Simulator (SMARTS), a distributed microscopic traffic simulator that can utilize multiple independent processes in parallel. SMARTS can perform fast large-scale simulations. For example, when simulating 1 million vehicles in an area the size of Melbourne, the system runs 1.14 times faster than real time with 30 computing nodes and 0.2s simulation timestep. SMARTS supports various driver models and traffic rules, such as the car-following model and lane-changing model, which can be driver dependent. It can simulate multiple vehicle types, including bus and tram. The simulator is equipped with a wide range of features that help to customize, calibrate, and monitor simulations. Simulations are accurate and confirm with real traffic behaviours. For example, it achieves 79.1% accuracy in predicting traffic on a 10km freeway 90 minutes into the future. The simulator can be used for predictive traffic advisories as well as traffic management decisions as simulations complete well ahead of real time. SMARTS can be easily deployed to different operating systems as it is developed with the standard Java libraries.

Intelligent personal assistants on mobile devices such as Apple’s Siri and Microsoft Cortana are increasingly important. Instead of passively reacting to queries, they provide users with brand new proactive experiences that aim to offer the right information at the right time. It is, therefore, crucial for personal assistants to understand users’ intent, that is, what information users need now. Intent is closely related to context. Various contextual signals, including spatio-temporal information and users’ activities, can signify users’ intent. It is, however, challenging to model the correlation between intent and context. Intent and context are highly dynamic and often sequentially correlated. Contextual signals are usually sparse, heterogeneous, and not simultaneously available. We propose an innovative collaborative nowcasting model to jointly address all these issues. The model effectively addresses the complex sequential and concurring correlation between context and intent and recognizes users’ real-time intent with continuously arrived contextual signals. We extensively evaluate the proposed model with real-world data sets from a commercial personal assistant. The results validate the effectiveness the proposed model, and demonstrate its capability of handling the real-time flow of contextual signals. The studied problem and model also provide inspiring implications for new paradigms of recommendation on mobile intelligent devices.

With the rapidly growing availability of vehicle trajectory data, travel costs such as travel time and fuel consumption can be captured accurately as distributions (e.g., travel time distributions) instead of deterministic values (e.g., average travel times). We study a new path finding problem in uncertain road networks, where paths have travel cost distributions. Given a source and a destination, we find optimal, non-dominated paths connecting the source and the destination, where the optimality is defined in terms of the stochastic dominance among cost distributions of paths. We first design an A based framework that utilizes the uncertain graph to obtain the most accurate cost distributions while finding the candidate paths. Next, we propose a three-stage dominance examination method that employs extreme values in each candidate path's cost distribution for early detection of dominated paths, thus reducing the need for expensive distributions convolutions. We conduct extensive experiments using real world road network and trajectory data. The results show that our algorithm outperforms baseline algorithms by up to two orders of magnitude in terms of query response time while achieving the most accurate results.

We revisit the moving k nearest neighbor (MkNN) query, which computes one's k nearest neighbor set and maintains it while at move. Existing MkNN algorithms are mostly safe region based, which lack efficiency due to either computing small safe regions with a high recomputation frequency or computing larger safe regions but with a high cost for each computation. In this demonstration, we showcase a system named INSQ that adopts a novel algorithm called the Influential Neighbor Set (INS) algorithm to process the MkNN query in both two-dimensional Euclidean space and road networks. This algorithm uses a small set of safe guarding objects instead of safe regions. As long as the the current k nearest neighbors are closer to the query object than the safe guarding objects are, the current k nearest neighbors stay valid and no recomputation is required. Meanwhile, the region defined by the safe guarding objects is the largest possible safe region. This means that the recomputation frequency is also minimized and hence, the INS algorithm achieves high overall query processing efficiency.

We study the problem of constructing a reverse nearest neighbor (RNN) heat map by finding the RNN set of every point in a two-dimensional space. Based on the RNN set of a point, we obtain a quantitative influence (i.e., heat) for the point. The heat map provides a global view on the influence distribution in the space, and hence supports exploratory analyses in many applications such as marketing and resource management. To construct such a heat map, we first reduce it to a problem called Region Coloring (RC), which divides the space into disjoint regions within which all the points have the same RNN set. We then propose a novel algorithm named CREST that efficiently solves the RC problem by labeling each region with the heat value of its containing points. In CREST, we propose innovative techniques to avoid processing expensive RNN queries and greatly reduce the number of region labeling operations. We perform detailed analyses on the complexity of CREST and lower bounds of the RC problem, and prove that CREST is asymptotically optimal in the worst case. Extensive experiments with both real and synthetic data sets demonstrate that CREST outperforms alternative algorithms by several orders of magnitude.

A new paradigm of recommendation is emerging in intelligent personal assistants such as Apple's Siri, Google Now, and Microsoft Cortana, which recommends "the right information at the right time" and proactively helps you "get things done". This type of recommendation requires precisely tracking users' contemporaneous intent, i.e., what type of information (e.g., weather, stock prices) users currently intend to know, and what tasks (e.g., playing music, getting taxis) they intend to do. Users' intent is closely related to context, which includes both external environments such as time and location, and users' internal activities that can be sensed by personal assistants. The relationship between context and intent exhibits complicated co-occurring and sequential correlation, and contextual signals are also heterogeneous and sparse, which makes modeling the context intent relationship a challenging task. To solve the intent tracking problem, we propose the Kalman filter regularized PARAFAC2 (KP2) nowcasting model, which compactly represents the structure and co-movement of context and intent. The KP2 model utilizes collaborative capabilities among users, and learns for each user a personalized dynamic system that enables efficient nowcasting of users' intent. Extensive experiments using real-world data sets from a commercial personal assistant show that the KP2 model significantly outperforms various methods, and provides inspiring implications for deploying large-scale proactive recommendation systems in personal assistants.

Mobile digital assistants such as Microsoft Cortana and Google Now currently offer appealing proactive experiences to users, which aim to deliver the right information at the right time. To achieve this goal, it is crucial to precisely predict users' real-time intent. Intent is closely related to context, which includes not only the spatial-temporal information but also users' current activities that can be sensed by mobile devices. The relationship between intent and context is highly dynamic and exhibits chaotic sequential correlation. The context itself is often sparse and heterogeneous. The dynamics and co-movement among contextual signals are also elusive and complicated. Traditional recommendation models cannot directly apply to proactive experiences because they fail to tackle the above challenges. Inspired by the nowcasting practice in meteorology and macroeconomics, we propose an innovative collaborative nowcasting model to effectively resolve these challenges. The proposed model successfully addresses sparsity and heterogeneity of contextual signals. It also effectively models the convoluted correlation within contextual signals and between context and intent. Specifically, the model first extracts collaborative latent factors, which summarize shared temporal structural patterns in contextual signals, and then exploits the collaborative Kalman Filter to generate serially correlated personalized latent factors, which are utilized to monitor each user's real-time intent. Extensive experiments with real-world data sets from a commercial digital assistant demonstrate the effectiveness of the collaborative nowcasting model. The studied problem and model provide inspiring implications for new paradigms of recommendations on mobile intelligent devices.

As a major type of continuous spatial queries, the moving$k$nearest neighbor ($k$NN) query has been studied extensively. However, most existing studies have focused on only the query efficiency. In this paper, we consider further the usability of the query results, in particular the diversification of the returned data points. We thereby formulate a new type of query named themoving$k$diversified nearest neighbor query (M$k$DNN). This type of query continuously reports the$k$diversified nearest neighbors while the query object is moving. Here, the degree of diversity of the$k$NN set is defined on the distance between the objects in the$k$NN set. Computing the$k$diversified nearest neighbors is an NP-hard problem. We propose an algorithm to maintain incrementally the$k$diversified nearest neighbors to reduce the query processing costs. We further propose two approximate algorithms to obtain even higher query efficiency with precision bounds. We verify the effectiveness and efficiency of the proposed algorithms both theoretically and empirically. The results confirm the superiority of the proposed algorithms over the baseline algorithm.

We study a new type of queries called the k-nearest neigh-bor temporal aggregate (kNNTA) query. Given a query point and a time interval, it returns the top-k locations that have the smallest weighted sums of (i) the spatial distance to the query point and (ii) a temporal aggregate on a cer-tain attribute over the time interval. For example, find a nearby club that has the largest number of people visiting in the last hour. This type of queries has emerging applica-tions in location-based social networks, location-based mo-bile advertising and social event recommendation. It is a great challenge to efficiently answer the query due to the highly dynamic nature and the large volume of the data and queries. To address this challenge, we propose an index named TAR-tree, which organizes locations by integrating the spatial and temporal aggregate information. We per-form a detailed analysis on the cost of processing kNNTA queries using the TAR-tree. The analysis shows that the TAR-tree results in much fewer node accesses than alterna-tives. Furthermore, we propose two enhancements for the kNNTA query: (i) an algorithm suggesting the least amount of weights to be adjusted to explore different query results and (ii) a collective processing scheme to share index traver-sal among a batch of queries. We conduct extensive exper-iments using real-world data sets. The results validate the accuracy of the cost analysis and show that the TAR-tree outperforms alternatives by up to ten times in node accesses. The results also show that the weight adjustment algorithm and collective processing scheme outperform their baselines by significant margins. 1.

We define and study Euclidean and spatial network variants of a new path finding problem: given a set of safe zones, find paths that minimize the distance traveled outside the safe zones. In this problem, the entire space with the exception of the safe zones is unsafe, but passable, and it differs from problems that involve unsafe regions to be strictly avoided. As a result, existing algorithms are not effective solutions to the new problem. To solve the Euclidean variant, we devise a transformation of the continuous data space with safe zones into a discrete graph upon which shortest path algorithms apply. A naïve transformation yields a very large graph that is expensive to search. In contrast, our transformation exploits properties of hyperbolas in the Euclidean space to safely eliminate graph edges, thus improving performance without affecting the shortest path results. To solve the spatial network variant, we propose a different graph-to-graph transformation that identifies critical points that serve the same purpose as do the hyperbolas, thus avoiding the creation of extraneous edges. This transformation can be extended to support a weighted version of the problem, where travel in safe zones has non-zero cost. We conduct extensive experiments using both real and synthetic data. The results show that our approaches outperform baseline approaches by more than an order of magnitude in graph construction time, storage space and query response time.

A hypergraph allows a hyperedge to connect more than two vertices, using which to capture the high-order relationships, many hypergraph learning algorithms are shown highly effective in various applications. When learning large hypergraphs, converting them to graphs to employ the distributed graph frameworks is a common approach, yet it results in major efficiency drawbacks including an inflated problem size, the excessive replicas, and the unbalanced workloads. To avoid such drawbacks, we take a different approach and propose HyperX, which is a thin layer built upon Spark. To preserve the problem size, HyperX directly operates on a distributed hypergraph. To reduce the replicas, HyperX replicates the vertices but not the hyperedges. To balance the workloads, we investigate the hypergraph partitioning problem aiming at minimizing the space and the communication cost subject to two separate constraints on the hyperedge and the vertex workloads. With experiments on both real and synthetic datasets, we verify that HyperX significantly improves the efficiency of the learning algorithms when compared with the graph conversion approach.

Semi-supervised learning is an essential approach to classification when the available labeled data is insufficient and we need to also make use of unlabeled data in the learning process. Numerous research efforts have focused on designing algorithms to improve the F1 score, but have any mechanism to control precision or recall individually. However, many applications have precision/recall preferences. For instance, an email spam classifier requires a precision of 0.9 to mitigate the false dismissal of useful emails. In this paper, we propose a method that allows to specify a precision/recall preference while maximising the F1 score. Our key idea is that we divide the semi-supervised learning process into multiple rounds of supervised learning, and the classifier learned at each round is calibrated using a sub-set of the labeled dataset before we use it on the unlabeled dataset for enlarging the training dataset. Our idea is applicable to a number of learning models such as Support Vector Machines (SVMs), Bayesian networks and neural networks. We focus our research and the implementation of our idea on SVMs. We conduct extensive experiments to validate the effectiveness of our method. The experimental results show that our method can train classifiers with a precision/recall preference, while the popular semi-supervised SVM training algorithm (which we use as the baseline) cannot. When we specify the precision preference and the recall preference to be the same, which indicates to maximise the F1 score only as the baseline does, our method achieves better or similar F1 scores to the baseline. An additional advantage of our method is that it converges much faster than the baseline.

The Earth Mover's Distance (EMD) similarity join retrieves pairs of records with EMD below a given threshold. It has a number of important applications such as near duplicate image retrieval and pattern analysis in probabilistic datasets. However, the computational cost of EMD is super cubic to the number of bins in the histograms used to represent the data objects. Consequently, the EMD similarity join operation is prohibitive for large datasets. This is the first paper that specifically addresses the EMD similarity join and we propose to use MapReduce to approach this problem. The MapReduce algorithms designed for generic metric distance similarity joins are inefficient for the EMD similarity join because they involve a large number of distance computations and have unbalanced workloads on reducers when dealing with skewed datasets. We propose a novel framework, named Melody-Join, which transforms data into the space of EMD lower bounds and performs pruning and partitioning at a low cost because computing these EMD lower bounds has a constant complexity. Furthermore, we address two key problems, the limited pruning power and the unbalanced workloads, by enhancing each phase in the Melody-Join framework. We conduct extensive experiments on real datasets. The results show that Melody-Join outperforms the state-of-the-art technique by an order of magnitude, scales up better on large datasets than the state-of-the-art technique, and scales out well on distributed machines.

Cross-validation is a commonly used method for evaluating the effectiveness of Support Vector Machines (SVMs). However, existing SVM cross-validation algorithms are not scalable to large datasets because they have to (i) hold the whole dataset in memory and/or (ii) perform a very large number of kernel value computation. In this paper, we propose a scheme to dramatically improve the scalability and efficiency of SVM cross-validation through the following key ideas. (i) To avoid holding the whole dataset in the memory and avoid performing repeated kernel value computation, we precompute the kernel values and reuse them. (ii) We store the precomputed kernel values to a high-speed storage framework, consisting of CPU memory extended by solid state drives (SSDs) and GPU memory as a cache, so that reusing (i.e., Reading) kernel values takes much lesser time than computing them on-the-fly. (iii) To further improve the efficiency of the SVM training, we apply a number of techniques for the extreme example search algorithm, design a parallel kernel value read algorithm, propose a caching strategy well-suited to the characteristics of the storage framework, and parallelize the tasks on the GPU and the CPU. For datasets of sizes that existing algorithms can handle, our scheme achieves several orders of magnitude of speedup. More importantly, our scheme enables SVM cross-validation on datasets of very large scale that existing algorithms are unable to handle.

The moving k nearest neighbor query, which computes one's k nearest neighbor set and maintains it while at move, is gaining importance due to the prevalent use of smart mobile devices such as smart phones. Safe region is a popular technique in processing the moving k nearest neighbor query. It is a region where the movement of the query object does not cause the current k nearest neighbor set to change. Processing a moving k nearest neighbor query is a continuing process of checking the validity of the safe region and recomputing it if invalidated. The size of the safe region largely decides the frequency of safe region recomputation and hence query processing efficiency. Existing moving k nearest neighbor algorithms lack efficiency due to either computing small safe regions and have to recompute frequently or computing large safe regions (i.e., an order- k Voronoi cell) with a high cost. In this paper, we take a third approach. Instead of safe regions, we use a small set of safe guarding objects. We prove that, as long as the the current k nearest neighbors are closer to the query object than the safe guarding objects, the current k nearest neighbors stay valid and no recomputation is required. This way, we avoid the high cost of safe region recomputation. We also prove that, the region defined by the safe guarding objects is the largest possible safe region. This means that the recomputation frequency of our method is also minimized. We conduct extensive experiments comparing our method with the state-of-the-art method on both real and synthetic data sets. The results confirm the superiority of our method.

We are experiencing the expanding use of location-based services such as AT&T’s TeleNav GPS Navigator and Intel’s Thing Finder. Existing location-based services have collected a large amount of location data, which has great potential for statistical usage in applications like traffic flow analysis, infrastructure planning, and advertisement dissemination. The key challenge is how to wisely use the data without violating each user’s location privacy concerns. In this article, we first identify a new privacy problem, namely, the inference-route problem, and then present our anonymization algorithms for privacy-preserving trajectory publishing. The experimental results have demonstrated that our approach outperforms the latest related work in terms of both efficiency and effectiveness.

Topic modeling has become a widely used tool for document management. However, there are few topic models distinguishing the importance of documents on different topics. In this paper, we propose a framework LIMTopic to incorporate link based importance into topic modeling. To instantiate the framework, RankTopic and HITSTopic are proposed by incorporating topical pagerank and topical HITS into topic modeling respectively. Specifically, ranking methods are first used to compute the topical importance of documents. Then, a generalized relation is built between link importance and topic modeling. We empirically show that LIMTopic converges after a small number of iterations in most experimental settings. The necessity of incorporating link importance into topic modeling is justified based on KL-Divergences between topic distributions converted from topical link importance and those computed by basic topic models. To investigate the document network summarization performance of topic models, we propose a novel measure called log-likelihood of ranking-integrated document-word matrix. Extensive experimental results show that LIMTopic performs better than baseline models in generalization performance, document clustering and classification, topic interpretability and document network summarization performance. Moreover, RankTopic has comparable performance with relational topic model (RTM) and HITSTopic performs much better than baseline models in document clustering and classification.

Conventional spatial indexes, represented by the R-tree, employ multidimensional tree structures that are complicated and require enormous efforts to implement in a full-fledged database management system (DBMS). An alternative approach for supporting spatial queries is mapping-based indexing, which maps both data and queries into a one-dimensional space such that data can be indexed and queries can be processed through a one-dimensional indexing structure such as the B + . Mapping-based indexing requires implementing only a few mapping functions, incurring much less effort in implementation compared to conventional spatial index structures. Yet, a major concern about using mapping-based indexes is their lower efficiency than conventional tree structures. In this article, we propose a mapping-based spatial indexing scheme called Size Separation Indexing (SSI). SSI is equipped with a suite of techniques including size separation, data distribution transformation, and more efficient mapping algorithms. These techniques overcome the drawbacks of existing mapping-based indexes and significantly improve the efficiency of query processing. We show through extensive experiments that, for window queries on spatial objects with nonzero extents , SSI has two orders of magnitude better performance than existing mapping-based indexes and competitive performance to the R-tree as a standalone implementation. We have also implemented SSI on top of two off-the-shelf DBMSs, PostgreSQL and a commercial platform, both having R-tree implementation. In this case, SSI is up to two orders of magnitude faster than their provided spatial indexes. Therefore, we achieve a spatial index more efficient than the R-tree in a DBMS implementation that is at the same time easy to implement. This result may upset a common perception that has existed for a long time in this area that the R-tree is the best choice for indexing spatial objects.

Destination prediction is an essential task for many emerging location based applications such as recommending sightseeing places and targeted advertising based on destination. A common approach to destination prediction is to derive the probability of a location being the destination based on historical trajectories. However, existing techniques using this approach suffer from the “data sparsity problem”, i.e., the available historical trajectories is far from being able to cover all possible trajectories. This problem considerably limits the number of query trajectories that can obtain predicted destinations. We propose a novel method named Sub-Trajectory Synthesis (SubSyn) algorithm to address the data sparsity problem. SubSyn algorithm first decomposes historical trajectories into sub-trajectories comprising two neighbouring locations, and then connects the sub-trajectories into “synthesised” trajectories. The number of query trajectories that can have predicted destinations is exponentially increased by this means. Experiments based on real datasets show that SubSyn algorithm can predict destinations for up to ten times more query trajectories than a baseline algorithm while the SubSyn prediction algorithm runs over two orders of magnitude faster than the baseline algorithm. In this paper, we also consider the privacy protection issue in case an adversary uses SubSyn algorithm to derive sensitive location information of users. We propose an efficient algorithm to select a minimum number of locations a user has to hide on her trajectory in order to avoid privacy leak. Experiments also validate the high efficiency of the privacy protection algorithm.

Destination prediction is an essential task for a number of emerging location based applications such as recommending sightseeing places and sending targeted advertisements. A common approach to destination prediction is to derive the probability of a location being the destination based on historical trajectories. However, existing techniques suffer from the "data sparsity problem", i.e., the number of available historical trajectories is far from sufficient to cover all possible trajectories. This problem considerably limits the amount of query trajectories whose predicted destinations can be inferred. In this demonstration, we showcase a system named "DesTeller" that is interactive, user-friendly, publicly accessible, and capable of answering real-time queries. The underlying algorithm Sub-Trajectory Synthesis (SubSyn) successfully addressed the data sparsity problem and is able to predict destinations for almost every query submitted by travellers. We also consider the privacy protection issue in case an adversary uses SubSyn algorithm to derive sensitive location information of users.

Given a set of client locations, a set of facility locations where each facility has a service capacity, and the assumptions that: (i) a client seeks service from its nearest facility; (ii) a facility provides service to clients in the order of their proximity, we study the problem of selecting all possible locations such that setting up a new facility with a given capacity at these locations will maximize the number of served clients. This problem has wide applications in practice, such as setting up new distribution centers for online sales business and building additional base stations for mobile subscribers. We formulate the problem as location selection query for utility maximization. After applying three pruning rules to a baseline solution,we obtain an efficient algorithm to answer the query. Extensive experiments confirm the efficiency of our proposed algorithm.

The volume of time series data grows rapidly in various applications such as network traffic management, telecommunications, finance and sensor network. To reduce the cost of storage, transmission and processing of time series data, the need for more compact representations of time series data is compelling. Segmentation is one of the most commonly used methods to meet this requirement. Both PLA and PPA are common segmentation methods which divide a time series into segments and use a linear function or a polynomial function to approximate each segment, respectively. However, while most of the current PLA and PPA methods aim to minimize the holistic error between the approximation and the original time series, few works try to represent time series as compact as possible with an error bound guarantee on each data point. Furthermore, in many real world situations, the patterns of the time series do not follow a constant rule such that using only one type of functions may not yield the best compaction.

We propose and study a new type of location optimization problem: given a set of clients and a set of existing facilities, we select a location from a given set of potential locations for establishing a new facility so that the average distance between a client and her nearest facility is minimized. We call this problem the min-dist location selection problem, which has a wide range of applications in urban development simulation, massively multiplayer online games, and decision support systems. We explore two common approaches to location optimization problems and propose methods based on those approaches for solving this new problem. However, those methods either need to maintain an extra index or fall short in efficiency. To address their drawbacks, we propose a novel method (named MND), which has very close performance to the fastest method but does not need an extra index. We provide a detailed comparative cost analysis on the various algorithms. We also perform extensive experiments to evaluate their empirical performance and validate the efficiency of the MND method.

Topic modeling has become a widely used tool for document management due to its superior performance. However, there are few topic models distinguishing the importance of documents on different topics. In this paper, we investigate how to utilize the importance of documents to improve topic modeling and propose to incorporate link based ranking into topic modeling. Specifically, topical pagerank is used to compute the topic level ranking of documents, which indicates the importance of documents on different topics. By retreating the topical ranking of a document as the probability of the document involved in corresponding topic, a generalized relation is built between ranking and topic modeling. Based on the relation, a ranking based topic model Rank Topic is proposed. With Rank Topic, a mutual enhancement framework is established between ranking and topic modeling. Extensive experiments on paper citation data and Twitter data are conducted to compare the performance of Rank Topic with that of some state-of-the-art topic models. Experimental results show that Rank Topic performs much better than some baseline models and is comparable with the state-of-the-art link combined relational topic model (RTM) in generalization performance, document clustering and classification by setting a proper balancing parameter. It is also demonstrated in both quantitative and qualitative ways that topics detected by Rank Topic are more interpretable than those detected by some baseline models and still competitive with RTM.

There have been intense research interests in moving object indexing in the past decade. However, existing work did not exploit the important property of skewed velocity distributions. In many real world scenarios, objects travel predominantly along only a few directions. Examples include vehicles on road networks, flights, people walking on the streets, etc. The search space for a query is heavily dependent on the velocity distribution of the objects grouped in the nodes of an index tree. Motivated by this observation, we propose the velocity partitioning (VP) technique, which exploits the skew in velocity distribution to speed up query processing using moving object indexes. The VP technique first identifies the "dominant velocity axes (DVAs)" using a combination of principal components analysis (PCA) and k-means clustering. Then, a moving object index (e.g., a TPR-tree) is created based on each DVA, using the DVA as an axis of the underlying coordinate system. An object is maintained in the index whose DVA is closest to the object's current moving direction. Thus, all the objects in an index are moving in a near 1-dimensional space instead of a 2-dimensional space. As a result, the expansion of the search space with time is greatly reduced, from a quadratic function of the maximum speed (of the objects in the search range) to a near linear function of the maximum speed. The VP technique can be applied to a wide range of moving object index structures. We have implemented the VP technique on two representative ones, the TPR*-tree and the B x -tree. Extensive experiments validate that the VP technique consistently improves the performance of those index structures.

We study the problem of finding the shortest route between two locations that includes a stopover of a given type. An example scenario of this problem is given as follows: “On the way to Bob's place, Alice searches for a nearby take-away Italian restaurant to buy a pizza.” Assuming that Alice is interested in minimizing the total trip distance, this scenario can be modeled as a query where the current Alice's location (start) and Bob's place (destination) function as query points. Based on these two query points, we find the minimum detour object (MDO), i.e., a stopover that minimizes the sum of the distances: 1) from the start to the stopover, and 2) from the stopover to the destination. In a realistic location-based application environment, a user can be indecisive about committing to a particular detour option. The user may wish to browse multiple (k) MDOs before making a decision. Furthermore, when a user moves, the k{\rm MDO} results at one location may become obsolete. We propose a method for continuous detour query (CDQ) processing based on incremental construction of a shortest path tree. We conducted experimental studies to compare the performance of our proposed method against two methods derived from existing k-nearest neighbor querying techniques using real road-network data sets. Experimental results show that our proposed method significantly outperforms the two competitive techniques.

We propose and study a new type of facility location selection query, the top-k most influential location selection query. Given a set M of customers and a set F of existing facilities, this query finds k locations from a set C of candidate locations with the largest influence values, where the influence of a candidate location c (c in C) is defined as the number of customers in M who are the reverse nearest neighbors of c. We first present a naive algorithm to process the query. However, the algorithm is computationally expensive and not scalable to large datasets. This motivates us to explore more efficient solutions. We propose two branch and bound algorithms, the Estimation Expanding Pruning (EEP) algorithm and the Bounding Influence Pruning (BIP) algorithm. These algorithms exploit various geometric properties to prune the search space, and thus achieve much better performance than that of the naive algorithm. Specifically, the EEP algorithm estimates the distances to the nearest existing facilities for the customers and the numbers of influenced customers for the candidate locations, and then gradually refines the estimation until the answer set is found, during which distance metric based pruning techniques are used to improve the refinement efficiency. BIP only estimates the numbers of influenced customers for the candidate locations. But it uses the existing facilities to limit the space for searching the influenced customers and achieve a better estimation, which results in an even more efficient algorithm. Extensive experiments conducted on both real and synthetic datasets validate the efficiency of the algorithms.

With the growing use of location-based services, location privacy attracts increasing attention from users, industry, and the research community. While considerable effort has been devoted to inventing techniques that prevent service providers from knowing a user's exact location, relatively little attention has been paid to enabling so-called peer-wise privacy---the protection of a user's location from unauthorized peer users. This paper identifies an important efficiency problem in existing peer-privacy approaches that simply apply a filtering step to identify users that are located in a query range, but that do not want to disclose their location to the querying peer. To solve this problem, we propose a novel, privacy-policy enabled index called the PEB-tree that seamlessly integrates location proximity and policy compatibility. We propose efficient algorithms that use the PEB-tree for processing privacy-aware range and k NN queries. Extensive experiments suggest that the PEB-tree enables efficient query processing.

User privacy in location-based services has attracted great interest in the research community. We introduce a novel framework based on a decentralized architecture for privacy preserving group nearest neighbor queries. A group nearest neighbor (GNN) query returns the location of a meeting place that minimizes the aggregate distance from a spread out group of users; for example, a group of users can ask for a restaurant that minimizes the total travel distance from them. We identify the challenges in preserving user privacy for GNN queries and provide a comprehensive solution to this problem. In our approach, users provide their locations as regions instead of exact points to a location service provider (LSP) to preserve their privacy. The LSP returns a set of candidate answers that includes the actual group nearest neighbor. We develop a private filter that determines the actual group nearest neighbor from the retrieved candidate answers without revealing user locations to any involved party, including the LSP. We also propose an efficient algorithm to evaluate GNN queries with respect to the provided set of regions (the users' imprecise locations). An extensive experimental study shows the effectiveness of our proposed technique.

Detecting changes in stock prices is a well known problem in finance with important implications for monitoring and business intelligence. Forewarning of changes in stock price, can be made by the early detection of changes in the distributions of stock order numbers. In this paper, we address the change detection problem for streams of stock order numbers and propose a novel incremental detection algorithm. Our algorithm gains high accuracy and low delay by employing a natural Poisson distribution assumption about the nature of stock order streams. We establish that our algorithm is highly scalable and has linear complexity. We also experimentally demonstrate its effectiveness for detecting change points, via experiments using both synthetic and real-world datasets.

The huge amount of temporal data generated from many important applications call for a highly efficient and scalable version index. The TSB-tree has the potential of large scalability due to its unique feature of progressive migration of data to larger mediums. However, its traditional design optimized for two levels of the memory hierarchy (the main memory and the hard disk) undermines its potential for high efficiency in face of today's advances in hardware, especially CPU/cache speed and memory size. We propose a novel version index structure called the HV-tree. Different from all previous version index structures, the HV-tree has nodes of different sizes, each optimized for a level of the memory hierarchy. As data migrates to different levels of the memory hierarchy, the HV-tree will adjust the node size automatically to exploit the best performance of all levels of the memory hierarchy. Moreover, the HV-tree has a unique chain mechanism to maximally keep recent data in higher levels of the memory hierarchy. As a result, HV-tree is several times faster than the TSB-tree for point queries (query with single key and single time value), and up to 1000 times faster than the TSB-tree for key-range and time-range queries.

In many applications involving spatial objects, we are only interested in objects that are directly visible from query points. In this paper, we formulate the visible k nearest neighbor (VkNN) query and present incremental algorithms as a solution, with two variants differing in how to prune objects during the search process. One variant applies visibility pruning to only objects, whereas the other variant applies visibility pruning to index nodes as well. Our experimental results show that the latter outperforms the former. We further propose the aggregate VkNN query that finds the visible k nearest objects to a set of query points based on an aggregate distance function. We also propose two approaches to processing the aggregate VkNN query. One accesses the database via multiple VkNN queries, whereas the other issues an aggregate k nearest neighbor query to retrieve objects from the database and then re-rank the results based on the aggregate visible distance metric. With extensive experiments, we show that the latter approach consistently outperforms the former one.

This demonstration program presents the V*-kNN algorithm, an efficient algorithm to process moving k nearest neighbor queries (MkNN). The V*-kNN algorithm is based on a safe-region concept called the V*-Diagram. By incrementally maintaining the V*-Diagram, V*-kNN continuously provides accurate MkNN query results and supports dynamically changing values of k. Our approach exploits information regarding the current location of the query point and the search space in addition to the data objects. As a result, the V*-kNN has much smaller IO and computation costs than existing methods.

With recent advances in mobile computing technologies, mobile devices can now render 3D objects realistically. Many users of these devices such as tourists, mixed-reality gamers, and rescue officers, need real-time retrieval of 3D objects over a wireless network. Due to bandwidth and latency restrictions in mobile settings, efficient continuous retrieval of 3D objects remains a challenge. In this paper, we describe a motion-aware approach to this problem. We first introduce multi-resolution storage and retrieval methods for 3D data, which restrict access to only the necessary content based on the client's motion pattern. We then propose a motion-aware buffer management technique as well as an efficient index using multi-resolution representations of objects. Our experiments demonstrate the effectiveness of our solution to continuous retrieval of complex spatial data in mobile settings.

The continuous intersection join query is computationally expensive yet important for various applications on moving objects. No previous study has specifically addressed this query type. We can adopt a naive algorithm or extend an existing technique (TP-Join) to process the query. However, they compute the answer for either too long or too short a time interval, which results in either a very large computation cost per object update or too frequent answer updates, respectively. This motivates us to optimize the query processing in the time dimension. In this study, we achieve this optimization by introducing the new concept of time-constrained (TC) processing. Further, TC processing enables a set of effective improvement techniques on traditional intersection join algorithms. With a thorough experimental study, we show that our algorithm outperforms the best adapted existing solution by several orders of magnitude.

Immortal DB is a transaction time database system designed to enable high performance for temporal applications. It is built into a commercial database engine, Microsoft SQL Server. This paper describes how we integrated a temporal indexing technique, the TSB-tree, into Immortal DB to serve as the core access method. The TSB-tree provides high performance access and update for both current and historical data. A main challenge was integrating TSB-tree functionality while preserving original B+tree functionality, including concurrency control and recovery. We discuss the overall architecture, including our unique treatment of index terms, and practical issues such as uncommitted data and log management. Performance is a primary concern. To increase performance, versions are locally delta compressed, exploiting the commonality between adjacent versions of the same record. This technique is also applied to index terms in index pages. There is a tradeoff between query performance and storage space. We discuss optimizing performance regarding this tradeoff throughout the paper. The result of our efforts is a high-performance transaction time database system built into an RDBMS engine, which has not been achieved before. We include a thorough experimental study and analysis that confirms the very good performance that it achieves.

The moving k nearest neighbor (M k NN) query finds the k nearest neighbors of a moving query point continuously. The high potential of reducing the query processing cost as well as the large spectrum of associated applications have attracted considerable attention to this query type from the database community. This paper presents an incremental safe-region-based technique for answering M k NN queries, called the V*-Diagram. In general, a safe region is a set of points where the query point can move without changing the query answer. Traditional safe-region approaches compute a safe region based on the data objects but independent of the query location. Our approach exploits the current knowledge of the query point and the search space in addition to the data objects. As a result, the V*-Diagram has much smaller IO and computation costs than existing methods. The experimental results show that the V*-Diagram outperforms the best existing technique by two orders of magnitude.

This paper assumes a setting where a population of objects move continuously in the Euclidean plane. The position of each object, modeled as a linear function from time to points, is assumed known. In this setting, the paper studies the querying for dense regions. In particular, the paper defines a particular type of density query with desirable properties and then proceeds to propose an algorithm for the efficient computation of density queries. While the algorithm may exploit any existing index for the current and near-future positions of moving objects, the Bx-tree is used. The paper reports on an extensive empirical study, which elicits the performance properties of the algorithm.

Monitoring aggregates on IP traffic data streams is a compelling application for data stream management systems. The need for exploratory IP traffic data analysis naturally leads to posing related aggregation queries on data streams, that differ only in the choice of grouping attributes. In this paper, we address this problem of efficiently computing multiple aggregations over high speed data streams, based on a two-level LFTA/HFTA DSMS architecture, inspired by Gigascope.Our first contribution is the insight that in such a scenario, additionally computing and maintaining fine-granularity aggregation queries (phantoms) at the LFTA has the benefit of supporting shared computation. Our second contribution is an investigation into the problem of identifying beneficial LFTA configurations of phantoms and user-queries. We formulate this problem as a cost optimization problem, which consists of two sub-optimization problems: how to choose phantoms and how to allocate space for them in the LFTA. We formally show the hardness of determining the optimal configuration, and propose cost greedy heuristics for these independent sub-problems based on detailed analyses. Our final contribution is a thorough experimental study, based on real IP traffic data, as well as synthetic data, to demonstrate the effectiveness of our techniques for identifying beneficial configurations.

In this article, we present an efficient B + -tree based indexing method, called iDistance, for K-nearest neighbor (KNN) search in a high-dimensional metric space. iDistance partitions the data based on a space- or data-partitioning strategy, and selects a reference point for each partition. The data points in each partition are transformed into a single dimensional value based on their similarity with respect to the reference point. This allows the points to be indexed using a B + -tree structure and KNN search to be performed using one-dimensional range search. The choice of partition and reference points adapts the index structure to the data distribution.We conducted extensive experiments to evaluate the iDistance technique, and report results demonstrating its effectiveness. We also present a cost model for iDistance KNN search, which can be exploited in query optimization.

Multidimensional data points can be mapped to one-dimensional space to exploit single dimensional indexing structures such as the B + -tree. In this article we present a Generalized structure for data Mapping and query Processing (GiMP), which supports extensible mapping methods and query processing. GiMP can be easily customized to behave like many competent indexing mechanisms for multi-dimensional indexing, such as the UB-Tree, the Pyramid technique, the iMinMax, and the iDistance. Besides being an extendible indexing structure, GiMP also serves as a framework to study the characteristics of the mapping and hence the efficiency of the indexing scheme. Specifically, we introduce a metric called mapping redundancy to characterize the efficiency of a mapping method in terms of disk page accesses and analyze its behavior for point, range and kNN queries. We also address the fundamental problem of whether an efficient mapping exists and how to define such a mapping for a given data set.

The effectiveness of many existing high-dimensional indexing structures is limited to specific types of queries and workloads. For example, while the Pyramid technique and the iMinMax are efficient for window queries, the iDistance is superior for kNN queries. We present a new structure, called the P/sup +/-tree, that supports both window queries and kNN queries under different workloads efficiently. In the P/sup +/-tree, a B/sup +/-tree is employed to index the data points as follows. The data space is partitioned into subspaces based on clustering, and points in each subspace are mapped onto a single dimensional space using the Pyramid technique, and stored in the B/sup +/ -tree. The crux of the scheme lies in the transformation of the data which has two crucial properties. First, it maps each subspace into a hypercube so that the Pyramid technique can be applied. Second, it shifts the cluster center to the top of the pyramid, which is the case that the Pyramid technique works very efficiently. We present window and kNN query processing algorithms for the P/sup +/-tree. Through an extensive performance study, we show that the P/sup +/-tree has considerable speedup over the Pyramid technique and the iMinMax for window queries and outperforms the iDistance for kNN queries.