Steering Vector (SV) is a powerful technique for controlling Large Language Models (LLMs) by manipulating their activations without altering model weights. However, when constructed from sensitive data, SV poses significant privacy risks, as it may leak private information. Existing differential privacy (DP) techniques for constructing SV cannot be directly applied to training-based SV construction paradigms, which offer higher task performance. In this work, we present **PrivSV**, a general privacy-preserving approach for constructing SV with DP guarantees, compatible with arbitrary SV construction paradigms while maintaining high utility. In PrivSV, we propose three novel methods: a Layer-wise Noise-Resilient Reduction (LNR²) method to reduce the injected noise in high-dimensional SV; a Directional Prior Compensation (DPC) method to recover utility degraded by noise perturbation; and a Privacy-Aware Optimal Parameter Determination (POPD) method to adaptively maximize the performance of the final compensated SV. Extensive experiments on open-source LLMs of different families (i.e., LlaMa, Qwen, Mistral and Gemma) demonstrate that PrivSV outperforms several existing techniques across various privacy budgets.

Large language models (LLMs) can effectively handle outdated information through knowledge editing.However, current approaches face two key limitations: (I) Poor generalization: Most approaches rigidly inject new knowledge without ensuring that the model can use it effectively to solve practical problems.(II) Narrow scope: Current methods focus primarily on structured fact triples, overlooking the diverse unstructured forms of factual information (e.g., news, articles) prevalent in real-world contexts.To address these challenges, we propose a new paradigm: teaching LLMs to edit knowledge via Chain of Thoughts (CoTs) reasoning (CoT2Edit).We first leverage language model agents for both structured and unstructured edited data to generate CoTs, building high-quality instruction data.The model is then trained to reason over edited knowledge through supervised finetuning (SFT) and Group Relative Policy Optimization (GRPO).At inference time, we integrate Retrieval-Augmented Generation (RAG) to dynamically retrieve relevant edited facts for real-time knowledge editing.Experimental results demonstrate that our method achieves strong generalization across six diverse knowledge editing scenarios with just a single round of training on three open-source language models.The codes are available at https:// github.com/FredJDean/CoT2Edit.

Large Reasoning Models (LRMs) can exhibit step-by-step reasoning, reflection, and backtracking, but these behaviors are often unregulated, leading to overthinking.As a result, LRMs continue generating redundant reasoning even after reaching high-confidence conclusions.This increases inference cost and latency, limiting practical deployment.The root cause is the absence of an intrinsic mechanism to monitor the reasoning state and decide when to continue, backtrack, or stop.We propose MERA, a meta-cognitive reasoning framework that decouples reasoning from control to enable independent optimization of control strategies.MERA constructs high-quality reasoning-control supervision data via a takeoverbased pipeline, and transforms long-horizon traces into structured reasoning-control alternating sequences for training.The model is trained with supervised fine-tuning to internalize the structured separation, and further optimized with Control-Segment Policy Optimization (CSPO), which combines segment-wise GRPO with control masking to focus learning on control segments.Experiments across reasoning benchmarks show that MERA improves both efficiency and accuracy.

Tingfeng Hui, Pengyu Zhu, Bowen Ping, Ling Tang, Guanting Dong, Yaqi Zhang, Sen Su. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Yuanhe Zhang, Jiayu Tian, Yibo Zhang, Shilinlu Yan, Liang Lin, Zhenhong Zhou, Li Sun, Sen Su. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Graph neural networks (GNNs) have achieved significant success in graph representation learning and have been applied to various domains. However, many real-world graphs contain sensitive personal information, such as user profiles in social networks, raising serious privacy concerns when graph learning is performed using GNNs. To address this issue, locally private graph learning protocols have gained considerable attention. These protocols leverage the privacy advantages of local differential privacy (LDP) and the effectiveness of GNN's message-passing in calibrating noisy data, offering strict privacy guarantees for users' local data while maintaining high utility (e.g., node classification accuracy) for graph learning. Despite these advantages, such protocols may be vulnerable to data poisoning attacks, a threat that has not been considered in previous research. Identifying and addressing these threats is crucial for ensuring the robustness and security of privacy-preserving graph learning frameworks. This work introduces the first data poisoning attack targeting locally private graph learning protocols. The attacker injects fake users into the protocol, manipulates these fake users to establish links with genuine users, and sends carefully crafted data to the server, ultimately compromising the utility of private graph learning. The effectiveness of the attack is demonstrated both theoretically and empirically. In addition, several defense strategies have also been explored, but their limited effectiveness highlights the need for more robust defenses.

Hypergraphs are the natural description of higher-order interactions among objects, widely applied in social network analysis, cross-modal retrieval, etc. Hypergraph Neural Networks (HGNNs) have become the dominant solution for learning on hypergraphs. Traditional HGNNs are extended from message passing graph neural networks, following the homophily assumption, and thus struggle with the prevalent heterophilic hypergraphs that call for long-range dependence modeling. Existing solutions enlarge the message flow through the hypergraph bottleneck, mitigating the oversquashing issue and capturing long-range dependence. However, they often accelerate the loss of representation distinguishability in the repeated aggregations, leading to oversmoothing. This dilemma motivates an interesting question: Can we develop a unified mechanism that is agnostic to both homophilic and heterophilic hypergraphs? In this paper, we achieve the best of both worlds through the lens of Riemannian geometry, which provides the potential to adjust the message passing behavior in different regions. The key insight lies in the connection between oversquashing and hypergraph bottleneck within the framework of Riemannian manifold heat flow. Building on this, we propose the novel idea of locally adapting the bottlenecks of different subhypergraphs. The core innovation of the proposed mechanism is the design of an adaptive local (heat) exchanger. Specifically, it captures the rich long-range dependencies via the Robin condition, and preserves the representation distinguishability via source terms, thereby enabling heterophily-agnostic message passing with theoretical guarantees. Based on this theoretical foundation, we present a novel Heat-Exchanger with Adaptive Locality for Hypergraph Neural Network (HealHGNN), designed as a node-hyperedge bidirectional systems with linear complexity in the number of nodes and hyperedges. Extensive experiments on both homophilic and heterophilic cases show that HealHGNN achieves the state-of-the-art performance.

Retrieval-Augmented Generation (RAG) improves the performance of Large Language Models (LLMs) by retrieving and integrating relevant information from external knowledge bases, which helps generate more accurate responses. However, RAG is vulnerable to retrieval poisoning attacks , where attackers can induce LLM to produce inaccurate responses by injecting malicious documents into the retrieval process. In this article, we propose ShieldRAG , a novel defense framework designed to counteract retrieval poisoning attacks by reshaping the retrieval embedding space. ShieldRAG leverages a dual-strategy effect realized via a majority-consensus mechanism: ① Push : Implicitly forces the embedding of a user query away from malicious documents by filtering out their minority signals, reducing their influence. ② Pull : Aligns the embedding of a user query closer to that of benign documents, reinforcing accurate retrieval. These strategies work synergistically to preserve retrieval integrity and enhance the quality of LLM-generated responses. Specifically, ShieldRAG operates through three key steps: Sliding Retrieval Explanation Generation , Keyword Aggregation , and Query Targeting Optimization . These three steps collectively ensure the effective integration of information from benign sources while filtering out malicious interference, thereby significantly enhancing the robustness of RAG systems against retrieval poisoning attacks. We evaluate ShieldRAG on four open-domain Question Answering (QA) datasets: Natural Questions, MS-MARCO, HotpotQA, and 2WikiMultiHopQA, using seven representative LLMs. Extensive experiments demonstrate that ShieldRAG significantly improves response accuracy while mitigating adversarial effects, showcasing strong generalization across multiple datasets and LLM architectures.

Mixture-of-Experts (MoE) shines brightly in large language models (LLMs) and demonstrates outstanding performance in plentiful natural language processing tasks.However, existing methods transforming LLMs from dense to MoE face significant data requirements and typically rely on large-scale post-training.In this paper, we propose Upcycling Instruction Tuning (UpIT), a data-efficient approach for tuning a dense pre-trained model into a MoE instruction model.Specifically, we first point out that intermediate checkpoints during instruction tuning of the dense model are naturally suitable for specialized experts, and then propose an expert expansion stage to flexibly achieve models with flexible numbers of experts, where genetic algorithm and parameter merging are introduced to ensure sufficient diversity of new extended experts.To ensure that each specialized expert in the MoE model works as expected, we select a small amount of seed data that each expert excels to preoptimize the router.Extensive experiments with various data scales and upcycling settings demonstrate the outstanding performance and data efficiency of UpIT, as well as stable improvement in expert or data scaling.Further analysis reveals the importance of ensuring expert diversity in upcycling.

Instruction tuning has become a cornerstone for unlocking the full potential of large language models. Among the key factors, complex and diverse instructions play a crucial role in aligning these models with a wide range of downstream tasks. However, current methodologies for constructing large-scale instruction datasets tend to favor powerful models, such as GPT-4, based on the empirical assumption that larger models inherently possess superior capabilities. In this study, we challenge this prevailing assumption and delve into the untapped potential of smaller language models (SLMs) in the context of instruction evolution. Through extensive experiments across three distinct scenarios of instruction evolution, we find that SLMs can generate more effective instructions compared to their larger counterparts. Further analysis reveals that SLMs exhibit a broader output space during instruction evolution, leading to the creation of more complex and diverse instructional variants. Additionally, we observe that existing evaluation metrics fall short in capturing the nuanced impact of instructions. To address this limitation, we propose Instruction Complex-Aware IFD (IC-IFD), an enhanced framework that incorporates instruction complexity into the original IFD score. This approach enables a more accurate assessment of the effectiveness of instruction data, paving the way for more refined instruction tuning strategies.

Large language models (LLMs) have shown strong potential in complex reasoning tasks.However, as task complexity increases, their performance often degrades, resulting in hallucinations, errors, and logical inconsistencies.To enhance reasoning capabilities, Monte Carlo Tree Search (MCTS) has been introduced to guide the exploration of reasoning paths in a structured manner.Despite its advantages, traditional MCTS relies on fixed reasoning strategies, limiting the diversity of reasoning paths and the coverage of the solution space.To address these limitations, we propose Dynamic Strategy-Guided MCTS (DSG-MCTS), a novel framework that dynamically integrates multiple reasoning strategies, such as abductive and analogical reasoning, to expand the reasoning space.At the same time, DSG-MCTS enhances reasoning efficiency through a dynamic strategy selection mechanism that adapts to the task context.Experimental results on challenging reasoning benchmarks demonstrate that DSG-MCTS achieves improved accuracy and efficiency, outperforming existing state-of-the-art methods.

Data heterogeneity poses a critical challenge in federated learning, driving the development of personalized client models. However, when each client’s local data is limited and nonindependent and identically distributed (non-IID), previous efforts fail to implement collaborative strategies based on the variability in data heterogeneity, thereby constraining the generalizability of the trained models. In this paper, we introduce a novel personalized Federated Learning method named FedCEMA, which tailors collaborative strategies to different scenarios of data heterogeneity. FedCEMA extracts prototype feature to align local objectives with the global optimum, and then calculates client-specific linear combinations of classifiers based on the similarity between clients.This allows clients to collaborate effectively by learning from those with similar data distributions, while maintaining personalized model benefits. Additionally, FedCEMA employs the Classifier Exponential Moving Average (CEMA) method, incorporating previously acquired knowledge to enhance the stability and efficiency of the model. Extensive experimental results on benchmark datasets demonstrate that our method improves both accuracy and stability compared to baselines.

Graph Neural Networks (GNNs) have demonstrated superior performance in a variety of graph mining and learning tasks. However, when node representations involve sensitive personal information or variables related to individuals, learning from graph data can raise significant privacy concerns. Although recent studies have explored local differential privacy (LDP) to address these concerns, they often introduce significant distortions to graph data, severely degrading private learning utility (e.g., node classification accuracy). In this paper, we present UPGNET, an LDP-based privacy-preserving graph learning framework that enhances utility while protecting user data privacy. Specifically, we propose a three-stage pipeline that generalizes the LDP protocols for node features, targeting privacy-sensitive scenarios. Our analysis identifies two key factors that affect the utility of privacy-preserving graph learning: feature dimension and neighborhood size. Based on the above analysis, UPGNET enhances utility by introducing two core layers: High-Order Aggregator (HOA) layer and the Node Feature Regularization (NFR) layer. Extensive experiments on real-world datasets indicate that UPGNET significantly outperforms existing methods in terms of both privacy protection and learning utility.

In this paper, we initiate the study of privacy-preserving graph diffusion models (DMs) for graph generation while protecting the privacy of edges in training graphs. We propose an Edge Private Graph Diffusion Model (EPGDiff) which enforces the model parameters to satisfy edge differential privacy (edge-DP) by clipping and perturbing gradients during training. In EPGDiff, since introducing DP noise into the model parameters significantly affects the utility of the generated graphs, we propose a Homophily Enhanced Denoising Network (HEDN) to enhance the utility of the generated graphs by leveraging the homophilic correlation between node attributes and graph structure. Moreover, we propose a Degree Preserving Graph Decoder (DPGD) to calibrate the generated graphs by utilizing the graph structure statistics, i.e., the node degree vector. Experimental results on real social graph datasets confirm the effectiveness of EPGDiff.

Ensuring that large language models (LLMs) remain both helpful and harmless poses a significant challenge: fine-tuning on repetitive safety datasets—where unsafe prompts are paired with standard refusal templates—often leads to \emph{false refusals}, in which benign queries are declined. We first quantify this effect, showing that safety data exhibits substantially lower token entropy ($H_{1}\approx9.18$) and 2-gram diversity ($\approx$ 0.048) compared to general instruction data ($H_{1}\approx12.05$, 2-gram$\approx$0.205). To uncover the root cause, we introduce \emph{FlowLens}, a stable PCA-based tool for residual-stream geometry analysis, and reveal that higher proportions of safety examples concentrate variance along a few components, reducing representational smoothness and driving false refusals (false refusal rate rises from 63\% to 84\% as safety data increases from 0\% to 40\%). Guided by these insights, we propose \emph{Variance Concentration Loss} (VCL), an auxiliary regularizer that penalizes excessive variance concentration in mid-layer residuals. Empirical results demonstrate that VCL reduces false refusals by over 35 percentage points while maintaining or improving performance on general benchmarks such as MMLU and GSM8K.

While large language models (LLMs) can solve PhD-level reasoning problems over long context inputs, they still struggle with a seemingly simpler task: following explicit length instructions—e.g., write a 10,000-word novel. Additionally, models often generate far too short outputs, terminate prematurely, or even refuse the request. Existing benchmarks focus primarily on evaluating generations quality, but often overlook whether the generations meet length constraints. To this end, we introduce Length Instruction Following Evaluation Benchmark (LIFEBench) to comprehensively evaluate LLMs' ability to follow length instructions across diverse tasks and a wide range of specified lengths. LIFEBench consists of 10,800 instances across 4 task categories in both English and Chinese, covering length constraints ranging from 16 to 8192 words. We evaluate 26 widely-used LLMs and find that most models reasonably follow short-length instructions but deteriorate sharply beyond a certain threshold. Surprisingly, almost all models fail to reach the vendor-claimed maximum output lengths in practice, as further confirmed by our evaluations extending up to 32K words. Even long-context LLMs, despite their extended input-output windows, counterintuitively fail to improve length-instructions following. Notably, Reasoning LLMs outperform even specialized long-text generation models, achieving state-of-the-art length following. Overall, LIFEBench uncovers fundamental limitations in current LLMs' length instructions following ability, offering critical insights for future progress.

Extreme Gradient Boosting (XGBoost) demonstrates excellent performance in practice and is widely used in both industry and academic research. This extensive application has led to a growing interest in employing multi-party data to develop more robust XGBoost models. In response to increasing concerns about privacy leakage, secure vertical federated XGBoost is proposed. It employs secure multi-party computation techniques, such as secret sharing (SS), to allow multiple parties holding vertically partitioned data, i.e., disjoint features on the same samples, to collaborate in constructing an XGBoost model. However, the running efficiency is the primary obstacle to the practical application of existing protocols, especially in multi-party settings. The reason is that these protocols not only require the execution of data-oblivious computations to protect intermediate results, leading to high computational complexity, but also involve a large number of SS-based non-linear operations with high overheads, e.g., division operations in gain score calculation and comparison operations in best split selection. To this end, we present a secure and efficient multi-party protocol for vertical federated XGBoost, called SecureXGB, which can perform the collaborative training of an XGBoost model in an SS-friendly manner. In SecureXGB, we first propose a parallelizable multi-party permutation method, which can secretly and efficiently permute all samples before model training to reduce the reliance on data-oblivious computations. Then, we design a linear gain score that can be evaluated without involving division operations and has equivalent utility to the original gain score. Finally, we develop a synchronous best split selection method to secretly identify the best split with the maximum gain score using a minimal number of comparison operations. Experimental results demonstrate that SecureXGB can achieve better training efficiency than state-of-the-art protocols without the loss of model accuracy.

User profiling has very important applications for many downstream tasks. Most existing methods only focus on modeling user profiles of one social network with plenty of data. However, user profiles are difficult to acquire, especially when the data is scarce. Fortunately, we observed that similar users have similar behavior patterns in different social networks. Motivated by such observations, in this paper, we for the first time propose to study the user profiling problem from the transfer learning perspective. We design two efficient frameworks for User Profile transferring acrOss Networks, i.e., UPON and E-UPON. In UPON, we first design a novel graph convolutional networks based characteristic-aware domain attention model to find user dependencies within and between domains (i.e., social networks). We then design a dual-domain weighted adversarial learning method to address the domain shift problem existing in the transferring procedure. In E-UPON, we optimize UPON in terms of computational complexity and memory. Specifically, we design a mini-cluster gradient descent based graph representation algorithm to shrink the searching space and ensure parallel computation. Then we use an adaptive cluster matching method to adjust the clusters of users. Experimental results on Twitter-Foursquare dataset demonstrate that UPON and E-UPON outperform the state-of-the-art models.

In vertical federated learning (VFL) settings, all parties obtain aligned samples of common users identified through private set intersection. For these aligned samples, each party holds disjoint features, while only the active party possesses the label information. As the initiator of model training, the active party can solely benefit from limited aligned samples, overlooking the valuable information contained in its non-aligned local samples. To address the constraint of failing to incorporate the active party's non-aligned samples in practical VFL, this paper presents aVerticalFederatedRepresentationSynthesis (VFedRS) approach for the active party. Its main idea is to transfer the knowledge of common samples to the active party's local feature space, thereby enhancing the performance of the task model trained locally within the active party. Specifically, we first propose a vertical federated principal component analysis module to extract accurate federated representations for common samples under privacy guarantees. To transfer knowledge from federated representations, we then build an input-conditional generative model to synthesize non-aligned samples' representations for the active party. Subsequently, the active party can leverage data representations to locally train any type of machine learning model suited to the downstream task. We conduct extensive experiments on two tabular datasets and two image datasets in the vertically partitioned setting, and the evaluation results validate the effectiveness of our approach.

Adversarial patches pose a significant threat to deep neural networks (DNNs). Unlike conventional adversarial attacks that are digital and less effective in the real world, adversarial patches can disrupt DNNs in real-world scenarios with potentially catastrophic outcomes. Understanding the characteristics of these patches is crucial to comprehending this new form of adversarial attack. While prior research has primarily aimed at enhancing the success rate of adversarial patches on specific DNN models, the rise of federated learning (FL) introduces a novel attack vector. In this context, attackers could manipulate a DNN model’s learnable parameters by contributing models trained on poisoned data. To assess the feasibility and danger of adversarial patches in this context, we introduce a novel attack method named PoisonPatch. This method merges FL poisoning attacks with adversarial patch search, first poisoning a DNN-based image classifier through FL, and then employing an adversarial patch search algorithm to create patches that increase the success rate of the attacks. This dual approach, combining poisoning attacks with adversarial patches, results in patches that are more challenging for machines to detect than traditional poisoning attacks and less noticeable to the human eye than typical adversarial patches due to their natural appearance. Our extensive experimental results demonstrate that PoisonPatch surpasses current state-of-the-art methods, producing natural-looking patches while achieving a 100% attack success rate.

Large language models (LLMs) have been proven capable of memorizing their training data, which can be extracted through specifically designed prompts. As the scale of datasets continues to grow, privacy risks arising from memorization have attracted increasing attention. Quantifying language model memorization helps evaluate potential privacy risks. However, prior works on quantifying memorization require access to the precise original data or incur substantial computational overhead, making it difficult for applications in real-world language models. To this end, we propose a fine-grained, entity-level definition to quantify memorization with conditions and metrics closer to real-world scenarios. In addition, we also present an approach for efficiently extracting sensitive entities from autoregressive language models. We conduct extensive experiments based on the proposed, probing language models' ability to reconstruct sensitive entities under different settings. We find that language models have strong memorization at the entity level and are able to reproduce the training data even with partial leakages. The results demonstrate that LLMs not only memorize their training data but also understand associations between entities. These findings necessitate that trainers of LLMs exercise greater prudence regarding model memorization, adopting memorization mitigation techniques to preclude privacy violations.

Large language models are susceptible to jailbreak attacks, which can result in the generation of harmful content.While prior defenses mitigate these risks by perturbing or inspecting inputs, they ignore competing objectives, the underlying cause of alignment failures.In this paper, we propose Alignment-Enhanced Decoding (AED), a novel defense that employs adaptive decoding to address the root causes of jailbreak issues.We first define the Competitive Index to quantify alignment failures and utilize feedback from self-evaluation to compute postalignment logits.Then, AED adaptively combines Competitive Index and post-alignment logits with the original logits to obtain harmless and helpful distributions.Consequently, our method enhances safety alignment while maintaining helpfulness.We conduct experiments across five models and four common jailbreaks, with the results validating the effectiveness of our approach.Code is available at https://github.com/GIGABaozi/AED.

Relation triple extraction is an essential task in information extraction and knowledge graph construction. Despite recent advancements, existing methods still exhibit certain limitations. Firstly, they only employ generalized pre-trained models and do not consider the specificity of relation triple extraction tasks. Moreover, existing tagging-based approaches typically decompose the task into two subtasks, initially identifying subjects and subsequently identifying objects and relations. They solely focus on extracting relational triples from subject→object, neglecting that once the extraction of a subject fails, it fails in extracting all triples. To address these issues, we propose SuperLED, an innovative supervised contrastive learning based dual path triple extraction framework. Specifically, we design a supervised contrastive learning method that considers multiple positive samples per anchor rather than restricting it to only one positive. Furthermore, a penalty term is introduced to prevent excessive similarity between the subject and object. Our framework implements taggers in two paths, enabling triples extraction from subject→object and object→subject. Experimental results show that SuperLED achieves state-of-the-art results on the benchmark datasets and significantly improves the F1 score on Normal, SEO, EPO, and multiple relation extraction tasks.

Ancient history relies on the study of ancient characters. However, real-world scanned oracle characters are difficult to collect and annotate, posing a major obstacle for oracle character recognition (OrCR). Besides, serious abrasion and inter-class similarity also make OrCR more challenging. In this paper, we propose a novel unsupervised domain adaptation method for OrCR, which enables to transfer knowledge from labeled handprinted oracle characters to unlabeled scanned data. We leverage pseudo-labeling to incorporate the semantic information into adaptation and constrain augmentation consistency to make the predictions of scanned samples consistent under different perturbations, leading to the model robustness to abrasion, stain and distortion. Simultaneously, an unsupervised transition loss is proposed to learn more discriminative features on the scanned domain by optimizing both between-class and within-class transition probability . Extensive experiments show that our approach achieves state-of-the-art result on Oracle-241 dataset and substantially outperforms the recently proposed structure-texture separation network by 15.1%.

In energy storage systems for autonomous vehicles, flywheel energy storage machines still suffer from high rotating iron consumption, a weak rotor structure, and poor robustness. As a flywheel energy storage device, this study employs a homopolar machine with a doubly salient solid rotor to address these issues. It has a simple design, a strong rotor, and reduced rotational loss at high speeds. It is given a fuzzy incremental proportional integral derivative (FIPID) intelligent control strategy. A simulation experiment is used to implement the novel optimization method. The constant speed sensitivity is enhanced by a factor of 20, and the torque variation is reduced by a factor of 6. The modeling and testing data show that the simulation and experimental results are reasonable. This shows that the proposed improved FIPID controller system and the considered intelligent homopolar machine system are effective, precise, stable, and respond in a dynamic way. It will be considered for applications in flywheel energy storage systems for autonomous vehicles with stored energy up to 500 MJ and power ranges from KW to GW. Its application will enhance the energy storage capacity of autonomous vehicles.Note to Practitioners—In this research we considered the urgent need of flywheel energy-storage machine system of new-energy autonomous vehicle for high-speed machine and found out energy-efficient, environment-friendly and high-efficiency automatic control algorithm. Previous researches on energy-storage machine were mainly focused on heteropolar machines which tend to have defects such as large iron loss in rotation, low rotor structural strength and poor robustness, etc., resulting in limited energy conversion efficiency of the flywheel energy-storage machine of autonomous vehicle during high-speed operation. Very few people ever chose homopolar machine from high-speed machines for energy storage control. In this paper, we chose a new type of homopolar machine with topology structure to minimize the machine’s iron loss in high-speed rotation and to enhance the rotor’s structural strength. We also put forward a new control algorithm matching with this machine, in order to further improve the system control performances including control precision and reliability. The simulation experiment of fuzzy incremental PID control system of homopolar machine for flywheel energy storage of autonomous vehicle and the actual data-driven simulation result showed that this algorithm realized more precise speed regulation and better reduced faults like torque ripple than the classical PID control algorithm, and further improved the machine efficiency within the whole operating speed and power ranges, and realized the dual purposes of quick charge and stable and safe operation of the flywheel energy storage machine. This algorithm provides theoretical and data validation support for the application of the flywheel energy storage into the autonomous vehicle system. And it can be readily implemented and incorporated into large-scale industrial computing systems.

Multi-passage machine reading comprehension (MRC) aims to answer a question by multiple passages. Existing multi-passage MRC approaches have shown that employing passages with and without golden answers (i.e., labeled and unlabeled passages) for model training can improve prediction accuracy. However, when using the unlabeled passages, they either incur the wrong labeling problem or treat the labeled and unlabeled passages equally. In addition, they ignore the original passage information to verify the correctness of the answer. In this paper, we present MLDV-MRC, a novel approach for multi-passage MRC viaMulti-taskLearning andDualVerification. MLDV-MRC adopts the extract-then-select framework, where an extractor is first used to predict answer candidates, then a selector is used to choose the final answer. For the extractor, we adopt multi-task learning with generative adversarial training to train it by using both labeled and unlabeled passages. To train the extractor by backpropagation, we propose a hybrid method which combines boundary-based and content-based extracting methods to produce the answer candidate set and its representation. For the selector, we propose to leverage both the information from answer candidates and original passages to verify the final answer. In particular, we propose a global-local memory-augmented neural network to build the representations of original passages, which fuses the passage-level information and word-level information. The experimental results on three open-domain QA datasets confirm the effectiveness of our approach.

Network alignment aims to discover nodes in different networks belonging to the same identity. In recent years, the network alignment problem has aroused significant attentions in both industry and academia. With the rapid growth of information, the sizes of networks are usually very large and in most cases we only focus on the alignment of partial networks. However, under this circumstances, the collected network data may be highly biased, and the training and testing data are no longer i.i.d. (identically and independently distributed). Thus, it is difficult for the trained alignment model to have a good performance in the test set. To bridge this gap, in this paper, we propose a novelDomain generAlization based netWork aligNment approach termed as DAWN. Specifically, in DAWN, we first design a novel invariant feature extraction model which leverages adversarial learning to extract domain-invariant features. Then, we design a novel invariant network alignment model which can achieve global optimum and local optimum simultaneously to learn domain-invariant alignment patterns. Finally, we conduct extensive experiments on the benchmark dataset of Facebook-Twitter, and results show that DAWN can averagely achieve 14.01% higher Hits@k and 10.63% higher MRR@k compared with the state-of-the-art methods.

In this article, we study the problem of differentially private multi-party data sharing, where the involved parties assisted by a semi-honest curator collectively generate a shared dataset while satisfying differential privacy. Inspired by the success of data synthesis with the generative adversarial network (GAN), we propose a novel GAN-based differentially private multi-party data sharing approach named ATLAS. In ATLAS, we extend the original GAN to multiple discriminators, and let each party hold a discriminator while the curator holds a generator. To update the generator without compromising each party's privacy, we decompose the calculation of the generator's gradient and selectively sanitize thediscriminators’ responses. Additionally, we propose two methods to improve the utility of shared data, i.e., the collaborative discriminator filtering (CDF) method and the adaptive gradient perturbation (AGP) method. Specifically, the CDF method utilizes trained discriminators to refine synthetic records, while the AGP method adaptively adjusts the noise scale during training to reduce the impact of deferentially private noise on the final shared data. Extensive experiments on real-world datasets validate the superiority of our ATLAS approach.

Locations are usually necessary for task allocation in spatial crowdsourcing, which may put individual privacy in jeopardy without proper protection. Although existing studies have well explored the problem of location privacy protection in task allocation under geo-indistinguishability, they potentially assume the workers could perform any tasks, which might not be practical in reality. Moreover, they usually adopt planar laplacian mechanism to achieve geo-indistinguishability, which will introduce excessive noise due to its randomness and boundlessness. To this end, we propose a task alloCAtioNapproach via grOup-based noisEaddition under Geo-I, referred to asCANOE. Its main idea is that each worker uploads the noisy distances between his true location and the obfuscated locations of his preferred tasks instead of uploading his obfuscated location. In particular, to alleviate the total noise when conducting grouping, we put forward an optimized global grouping with adaptive local adjustment methodOGALwith convergence guarantee. To collect the noisy distances which are required for subsequent task allocation, we develop a utility-aware obfuscated distance collection methodUODCwith solid privacy and utility guarantees. We further theoretically analyze the privacy, utility and complexity guarantees ofCANOE. Extensive analyses and experiments over two real-world datasets confirm the effectiveness ofCANOE.

Truth discovery is an effective way to identify the aggregated truth of each task among multiple observed data drawn from different workers of varying reliabilities. However, existing studies are insufficient to protect individuals’ privacy, as they either just guarantee the weaker versions of local differential privacy (LDP) or potentially assume that the tasks are independent. In this paper, we, for the first time, investigate the problem of truth discovery while achieving the rigorous LDP for each worker with continuous inputs without the independence assumption. We present a locally differentially private truth discovery approach calledPrivTDSIbased on sampling and inference with solid privacy and utility guarantees. InPrivTDSI, the server first determines which values of each worker should be sampled according to a sample proportion and sends the indexes of these values to each worker. Then, each worker adds noise into the sampled values for privacy protection and uploads them to the server. After receiving the noisy sampled values from all the workers, the server first infers the unsampled values and then conducts truth discovery based on both the noisy sampled values and the inferred values. In particular, to determine the sample proportion, we formulate aconstrained nonlinear programmingproblem and give a closed-form solution to this problem. Moreover, to determine which values of each worker should be sampled while avoiding the situation where the values of some workers or tasks might not be sampled at all, we develop a two-stage sampling method calledTOSS. Furthermore, to infer the unsampled values accurately, we design a quality-aware inference method based on matrix factorization calledQualityMF. Experimental results on two real-world datasets and a synthetic dataset demonstrate the effectiveness of${PrivTDSI}$.

Social network alignment, identifying social accounts of the same individual across different social networks, shows fundamental importance in a wide spectrum of applications, such as link prediction and information diffusion. Individuals more often than not join in multiple social networks, and it is in fact much too expensive or even impossible to acquiring supervision for guiding the alignment. To the best of our knowledge, few method in the literature can align multiple social networks without supervision. In this article, we propose to study the problem of unsupervised multiple social network alignment. To address this problem, we propose a novel unsupervised model of joint Matrix factorization with a diagonal Cone under orthogonal Constraint, referred to as MC 2 . Its core idea is to embed and align multiple social networks in the common subspace via an unsupervised approach. Specifically, in MC 2 model, we first design a matrix optimization to infer the common subspace from different social networks. To address the nonconvex optimization, we then design an efficient alternating algorithm by leveraging its inherent functional property. Through extensive experiments on real-world datasets, we demonstrate that the proposed MC 2 model significantly outperforms the state-of-the-art methods.

With the deep penetration of the Internet and mobile devices, preference rankings are being collected on a massive scale by diverse data collectors for various business demands. However, users’ preference rankings in many applications are highly sensitive. Without proper privacy protection mechanisms, it either puts individual privacy in jeopardy or hampers business opportunities due to users’ unwillingness to share their true rankings. In this paper, we initiate the study of collecting preference rankings under local differential privacy. The key technical challenge comes from the fact that the number of possible rankings could be large in practical settings, leading to excessive injected noise. To solve this problem, we present a novel approach SAFARI, whose main idea is to collect a set of distributions over small domains which are carefully chosen based on the riffle independent (RI) model to approximate the overall distribution of users’ rankings, and then generate a synthetic ranking dataset from the obtained distributions. By working on small domains instead of a large domain, SAFARI can significantly reduce the magnitude of added noise. In SAFARI, we design two transformation rules, namely Rule I and Rule II, to instruct users to transform their data to provide the information about the distributions of the small domains. In particular, we propose a method called LADE to precisely estimate the required distributions used for the structure learning of RI model. We also propose a new LDP method called SAFA for frequency estimation over multiple attributes that have small domains. We formally prove that SAFARI guarantees$\varepsilon$-local differential privacy. Extensive experiments on real datasets confirm the effectiveness of SAFARI.

Social network alignment, aligning different social networks on their common users, is receiving dramatic attentions from both academic and industry. All existing studies consider the social network to be static and neglect its inherent dynamics. In fact, the dynamics of social networks contain the discriminative pattern of an individual, which can be leveraged to facilitate social network alignment. Hence, we for the first time propose to study the problem of aligning dynamic social networks. Towards this end, we propose a novel Dynamic Graph autoencoder based dynamic social network Alignment approach, referred to as DGA, unfolding the fruitful dynamics of social networks for user alignment. However, it faces challenges in both modeling and optimization: (1) To model the intra-network dynamics, we design a novel dynamic graph autoencoder to learn user embeddings with complex network dynamics. (2) To model the inter-network alignment, we design a unified optimization framework over proposed dynamic graph autoencoders, constructing a common subspace for user alignment across different networks. (3) To address this optimization problem, we design an effective alternating algorithm with solid theoretical guarantees. We conduct extensive experiments on real-world datasets and show that the proposed approach substantially outperforms the state-of-the-art methods.

Given a set of local sequential datasets held by multiple parties, we study the problem of publishing a synthetic dataset that preserves approximate sequentiality information of the integrated dataset while satisfying differential privacy for each local dataset. The existing solutions for publishing differentially private sequential data in the centralized setting mostly adopt tree-based approaches. Such approaches rely on different tree structures that encode sequential data's statistical information. The construction of a tree structure is normally done by recursively splitting nodes whose noisyscores(e.g., entropy or count) are larger than a given threshold. However, extending similar ideas to the multi-party setting is challenging. First, the comparison between noisy scores and a given threshold needs to be done in a distributed manner without letting the parties know the noisy scores, while satisfying differential privacy for each local dataset. Second, in the multi-party setting the large number of node splitting decisions incurs prohibitive computation costs. In addressing the above challenges, we presentDPST, a distributed prediction suffix tree construction solution. In DPST, we first introduce a novel node splitting decision method that calculates the comparison result under encryption with substantially improved efficiency. Then we present a novel batch-based tree construction approach to reduce computation costs. In order to achieve high parallel performance without incurring any extra communication cost, we introduce theconjunctionandslidemethods to ensure that each batch contains a stable number of carefully arrangeddecision tasks. To further reduce communication and computation costs, we propose a prefix-based pre-pruning method to reduce the number of nodes that need to be judged whether to split by an interactive protocol. Extensive experiments on real datasets demonstrate that our DPST solution offers desirable data utility with low computation and communication costs.

Network alignment aims to discover nodes in different networks belonging to the same identity. In recent years, the network alignment problem has aroused significant attentions in both industry and academia. However, the continuous exploding of network data brings two challenges in solving the network alignment problem, i.e., large network scale and scarce labeled data. To bridge this gap, in this paper we propose a novel approach termed asMulti-granularItyNetwork alIgnment based on coNtrastive learninG(MINING). Specifically, in MINING, we first design multi-granularity alignment framework to solve the issue of large network scale. Then, we design intra- and inter-network contrastive learning to solve the issue of scarce labeled data. Moreover, we provide theoretical proofs to demonstrate the effectiveness of MINING. Finally, we conduct extensive experiments on the benchmark datasets of Facebook-Twitter, AMiner-LinkedIn and DBpedia$_{\text{ZH}}$-DBpedia$_{\text{EN}}$, and results show that MINING can averagely achieve 15.93% higher$\operatorname{Hits@}k$and 14.82% higher$\operatorname{MRR@}k$compared with the state-of-the-art methods.

Recently, aligning users among different social networks has received significant attention. However, most of the existing studies do not consider users' behavior information during the aligning procedure and thus still suffer from poor learning performance. In fact, we observe that social network alignment and user behavior analysis can benefit from each other. Motivated by such an observation, we propose to jointly study the social network alignment and user behavior analysis problem in this paper. We design a novel framework named BANANA-RGB. In this framework, to capture users' multi-scale behavior information in each social network, we train a variant of the hierarchical periodic memory network with personalized memorization. To leverage behavior analysis for social network alignment, we design a tensor fusion network-based alignment component to improve the performance. To further leverage social network alignment for behavior analysis, we design a gating-based cross-network behavior fusion component to integrate users' behavior information in different social networks based on the alignment result. We iteratively train the above two components to make the two tasks benefit from each other. Extensive experiments on real-world datasets demonstrate that our proposed approach outperforms the state-of-the-art methods.

Graph representation learning received increasing attentions in recent years. Most of the existing methods ignore the complexity of the graph structures and restrict graphs in a single constant-curvature representation space, which is only suitable to particular kinds of graph structure indeed. Additionally, these methods follow the supervised or semi-supervised learning paradigm, and thereby notably limit their deployment on the unlabeled graphs in real applications. To address these aforementioned limitations, we take the first attempt to study the self-supervised graph representation learning in the mixed-curvature spaces. In this paper, we present a novel Self-Supervised Mixed-Curvature Graph Neural Network (SelfMGNN). To capture the complex graph structures, we construct a mixed-curvature space via the Cartesian product of multiple Riemannian component spaces, and design hierarchical attention mechanisms for learning and fusing graph representations across these component spaces. To enable the self-supervised learning, we propose a novel dual contrastive approach. The constructed mixed-curvature space actually provides multiple Riemannian views for the contrastive learning. We introduce a Riemannian projector to reveal these views, and utilize a well-designed Riemannian discriminator for the single-view and cross-view contrastive learning within and across the Riemannian views. Finally, extensive experiments show that SelfMGNN captures the complex graph structures and outperforms state-of-the-art baselines.

In this paper, we tackle the problem of collecting individual trajectories under local differential privacy. The key challenge is how to achieve high utility of the collected trajectories while satisfying the strong privacy guarantee. To overcome this challenge, we present a novel approach, which is referred to as PrivTC. In PrivTC, we first design a locally differentially private grid construction method to instruct the aggregator to lay an appropriate grid on the given geospatial domain. Then we propose a locally differentially private spectral learning method to help the aggregator learn the Hidden Markov Model (HMM) from users' trajectories discretized by the constructed grid. Finally, the aggregator generates a synthetic trajectory dataset as a surrogate for the original one from the learned HMM. Extensive experiments on real datasets confirm the effectiveness of PrivTC.

Event argument extraction (EAE) is an important information extraction task, which aims to identify the arguments of an event described in a given text and classify the roles played by them. A key characteristic in realistic EAE data is that the instance numbers of different roles follow an obvious long-tail distribution. However, the training and evaluation paradigms of existing EAE models either prone to neglect the performance on "tail roles'', or change the role instance distribution for model training to an unrealistic uniform distribution. Though some generic methods can alleviate the class imbalance in long-tail datasets, they usually sacrifice the performance of "head classes'' as a trade-off. To address the above issues, we propose to train our model on realistic long-tail EAE datasets, and evaluate the average performance over all roles. Inspired by the Mixture of Experts (MOE), we propose a Routing-Balanced Dual Expert Framework (RBDEF), which divides all roles into "head" and "tail" two scopes and assigns the classifications of head and tail roles to two separate experts. In inference, each encoded instance will be allocated to one of the two experts by a routing mechanism. To reduce routing errors caused by the imbalance of role instances, we design a Balanced Routing Mechanism (BRM), which transfers several head roles to the tail expert to balance the load of routing, and employs a tri-filter routing strategy to reduce the misallocation of the tail expert's instances. To enable an effective learning of tail roles with scarce instances, we devise Target-Specialized Meta Learning (TSML) to train the tail expert. Different from other meta learning algorithms that only search a generic parameter initialization equally applying to infinite tasks, TSML can adaptively adjust its search path to obtain a specialized initialization for the tail expert, thereby expanding the benefits to the learning of tail roles. In experiments, RBDEF significantly outperforms the state-of-the-art EAE models and advanced methods for long-tail data.

In network virtualization, one of the key problems is to embed a sequence of virtual networks with both node and link constraints onto the physical network, which is known to be NP-hard. Recent studies focus on how to minimize the energy cost while maximizing the revenue of the physical network when the VN request arrives. However, after a period of time, due to the dramatic dynamics of the resources of the physical network, the previous solution may become less energy efficient. In this article, we study how to re-optimize the energy cost by leveraging the migration technique. In particular, we first give the problem model of virtual network migration. Then we design two energy aware virtual network migration algorithms called EA-VNM and EA-VNM-G. For EA-VNM, it answers the following key questions: when to perform migration, migrate which virtual nodes to where, and how to perform migration. Especially, for EA-VNM-G, it further reduces the high time complexity problem of EA-VNM by grouping the virtual nodes to be migrated with fewer conflicts. Extensive simulations show that EA-VNM significantly reduces the energy cost by up to 25 percent over the state-of-the-art algorithm while maintaining similar revenue and EA-VNM-G reduces the running time significantly.

In social networks, one of the most significant challenges is how to estimate the tweet popularity. Prior studies focus on leveraging different aspects of just a single tweet, while ignoring the impact of historical tweets. In this article, we propose to leverage such historical information and rethink the problem of tweet popularity estimation. From historical information, there are two important factors that can be extracted: (1) user reputation feature, which can represent coarse-grained level of tweet popularity and (2) tweet related features, which can represent fine-grained level of tweet popularity. To incorporate these two factors from historical information, we design a novel deep neural architecture, a Bi-layered LSTM for tweet popUlarity Estimation, called DeepBlue. Specifically, we first propose a user-reputation aware mechanism to combine coarse-grained and fine-grained level estimation into a united LSTM model. We also design a content attention mechanism to consider different impacts of historical tweets in terms of content similarity. We then propose a time aware mechanism to address the time interval irregularity issue. Finally, we apply the Poisson regression model to obtain the overall loss for tweet popularity estimation. Extensive experiments demonstrate the superiority of our proposed approach to other state-of-the-arts in terms of MAE and SRC.

Relation extraction (RE), an important information extraction task, faced the great challenge brought by limited annotation data. To this end, distant supervision was proposed to automatically label RE data, and thus largely increased the number of annotated instances. Unfortunately, lots of noise relation annotations brought by automatic labeling become a new obstacle. Some recent studies have shown that the teacher-student framework of knowledge distillation can alleviate the interference of noise relation annotations via label softening. Nevertheless, we find that they still suffer from two problems: propagation of inaccurate dark knowledge and constraint of a unified distillation temperature . In this article, we propose a simple and effective Multi-instance Dynamic Temperature Distillation (MiDTD) framework, which is model-agnostic and mainly involves two modules: multi-instance target fusion (MiTF) and dynamic temperature regulation (DTR). MiTF combines the teacher’s predictions for multiple sentences with the same entity pair to amend the inaccurate dark knowledge in each student’s target. DTR allocates alterable distillation temperatures to different training instances to enable the softness of most student’s targets to be regulated to a moderate range. In experiments, we construct three concrete MiDTD instantiations with BERT, PCNN, and BiLSTM-based RE models, and the distilled students significantly outperform their teachers and the state-of-the-art (SOTA) methods.

Learning representations for graphs plays a critical role in a wide spectrum of downstream applications. In this paper, we summarize the limitations of the prior works in three folds: representation space, modeling dynamics and modeling uncertainty. To bridge this gap, we propose to learn dynamic graph representations in hyperbolic space, for the first time, which aims to infer stochastic node representations. Working with hyperbolic space, we present a novel Hyperbolic Variational Graph Neural Network, referred to as HVGNN. In particular, to model the dynamics, we introduce a Temporal GNN (TGNN) based on a theoretically grounded time encoding approach. To model the uncertainty, we devise a hyperbolic graph variational autoencoder built upon the proposed TGNN to generate stochastic node representations of hyperbolic normal distributions. Furthermore, we introduce a reparameterisable sampling algorithm for the hyperbolic normal distribution to enable the gradient-based learning of HVGNN. Extensive experiments show that HVGNN outperforms state-of-the-art baselines on real-world datasets.

User profiling is playing an increasingly important role in real-world applications. Previous works have shown that integrating user information from multiple social networks helps to significantly improve the performance of user profiling. However, these studies either ignore the different contributions of various features in different profiling tasks or need to train one model for each task. What’s more, the assumption of the strong relatedness between user profiling tasks limits their application. These phenomena make inferring comprehensive user attributes still an open problem. In this paper, we propose a novel method, called Hierarchical Attention-based Model with sparse-sharing-based muLti-task sElf-Training algorithm (HAMLET), for comprehensive user profiling. More specifically, we first employ a hierarchical attention-based network as our base network to represent users. It assigns various features from different social networks with different weights for different users during the fusing procedure. Then, we propose a multi-task self-training algorithm that takes advantage of both task correlations and self-training to obtain better performance. We conduct extensive experiments on two real-world datasets and verify the superiority of HAMLET for user profiling.

Event detection (ED) aims at identifying event instances of specified types in given texts, which has been formalized as a sequence labeling task.As far as we know, existing neural-based ED models make decisions relying on the contextual semantic features of each word in the input text, which we find is easy to get confused by varied contexts in the test stage.To this end, we come up with the idea of introducing a set of statistical features from word-event co-occurrence frequencies in the entire training set to cooperate with the contextual features.Specifically, we propose a Semantic and Statistic-Joint Discriminative Network (S 2 -JDN) consisting of a semantic feature extractor, a statistical feature extractor, and a joint event discriminator.In experiments, S 2 -JDN effectively exceeds ten recent state-ofthe-art (SOTA) baseline methods on ACE2005 and KBP2015 benchmark datasets.Further, we perform extensive experiments to investigate the effectiveness of S 2 -JDN.

Given a set of local sequential datasets held by multiple parties, we study the problem of publishing a synthetic dataset that preserves approximate sequentiality information of the integrated dataset while satisfying differential privacy for each local dataset. The existing solutions for publishing differentially private sequential data in the centralized setting mostly adopt tree-based approaches. Such approaches rely on different tree structures that encode sequential data's statistical information. The construction of a tree structure is normally done by recursively splitting nodes whose noisy scores (e.g., entropy or count) are larger than a given threshold. However, extending similar ideas to the multi-party setting is challenging. First, the comparison between noisy scores and a given threshold needs to be done in a distributed manner without letting the parties know the noisy scores, while satisfying differential privacy for each local dataset. Second, in the multi-party setting the large number of node splitting decisions incurs prohibitive computation costs. In addressing the above challenges, we present DPST, a distributed prediction suffix tree construction solution. In DPST, we first introduce a novel node splitting decision method that calculates the comparison result under encryption with substantially improved efficiency. Then we present a novel batch-based tree construction approach to reduce the computation costs. In order to achieve high parallel performance without incurring any extra communication cost, we introduce the conjunction and slide methods to ensure that each batch contains a stable number of carefully arranged decision tasks. Extensive experiments on real datasets demonstrate that our DPST solution offers desirable data utility with low computation and communication costs.

Inspired by the success of BERT, several multimodal representation learning approaches have been proposed that jointly represent image and text. These approaches achieve superior performance by capturing high-level semantic information from large-scale multimodal pretraining. In particular, LXMERT and UNITER adopt visual region feature regression and label classification as pretext tasks. However, they tend to suffer from the problems of noisy labels and sparse semantic annotations, based on the visual features having been pretrained on a crowdsourced dataset with limited and inconsistent semantic labeling. To overcome these issues, we propose unbiased Dense Contrastive Visual-Linguistic Pretraining (DCVLP), which replaces the region regression and classification with cross-modality region contrastive learning that requires no annotations. Two data augmentation strategies (Mask Perturbation and Intra-Inter-Adversarial Perturbation) are developed to improve the quality of negative samples used in contrastive learning. Overall, DCVLP allows cross-modality dense region contrastive learning in a self-supervised setting independent of any object annotations. We compare our method against prior visual-linguistic pretraining frameworks to validate the superiority of dense contrastive learning on multimodal representation learning.

Abstract Local community detection aims to find the communities that a given seed node belongs to. Most existing works on this problem are based on a very strict assumption that the seed node only belongs to a single community, but in real-world networks, nodes are likely to belong to multiple communities. In this paper, we first introduce a novel algorithm, HqsMLCD, that can detect multiple communities for a given seed node over static networks. HqsMLCD first finds the high-quality seeds which can detect better communities than the given seed node with the help of network representation, then expands the high-quality seeds one-by-one to get multiple communities, probably overlapping. Since dynamic networks also act an important role in practice, we extend the static HqsMLCD to handle dynamic networks and introduce HqsDMLCD. HqsDMLCD mainly integrates dynamic network embedding and dynamic local community detection into the static one. Experimental results on real-world networks demonstrate that our new method HqsMLCD outperforms the state-of-the-art multiple local community detection algorithms. And our dynamic method HqsDMLCD gets comparable results with the static method on real-world networks.

Abstract Entity linking is a fundamental task in natural language processing. The task of entity linking with knowledge graphs aims at linking mentions in text to their correct entities in a knowledge graph like DBpedia or YAGO2. Most of existing methods rely on hand‐designed features to model the contexts of mentions and entities, which are sparse and hard to calibrate. In this paper, we present a neural model that first combines co‐attention mechanism with graph convolutional network for entity linking with knowledge graphs, which extracts features of mentions and entities from their contexts automatically. Specifically, given the context of a mention and one of its candidate entities' context, we introduce the co‐attention mechanism to learn the relatedness between the mention context and the candidate entity context, and build the mention representation in consideration of such relatedness. Moreover, we propose a context‐aware graph convolutional network for entity representation, which takes both the graph structure of the candidate entity and its relatedness with the mention context into consideration. Experimental results show that our model consistently outperforms the baseline methods on five widely used datasets.

In this paper, we study the problem of publishing vertically partitioned data under differential privacy, where different attributes of the same set of individuals are held by multiple parties. In this setting, with the assistance of a semi-trusted curator, the involved parties aim to collectively generate an integrated dataset while satisfying differential privacy for each local dataset. Based on the latent tree model (LTM), we present a differentially private latent tree (DPLT) approach, which is, to the best of our knowledge, the first approach to solving this challenging problem. In DPLT, the parties and the curator collaboratively identify the latent tree that best approximates the joint distribution of the integrated dataset, from which a synthetic dataset can be generated. The fundamental advantage of adopting LTM is that we can use the connections between a small number of latent attributes derived from each local dataset to capture the cross-dataset dependencies of the observed attributes in all local datasets such that the joint distribution of the integrated dataset can be learned with little injected noise and low computation and communication costs. DPLT is backed up by a series of novel techniques, including two-phase latent attribute generation (TLAG), tree index based correlation quantification (TICQ) and distributed Laplace perturbation protocol (DLPP). Extensive experiments on real datasets demonstrate that DPLT offers desirable data utility with low computation and communication costs.

Recently, reconciling social networks, identifying the accounts belonging to the same individual across social networks, receives significant attention from both academic and industry. Most of the existing studies have limitations in the following three aspects: multiplicity, comprehensiveness and robustness. To address these limitations, we rethink this problem and, for the first time, robustly and comprehensively reconcile multiple social networks. In this paper, we propose two frameworks, MASTER and MASTER+, i.e., across Multiple social networks, integrate Attribute and STructure Embedding for Reconciliation. In MASTER, we first design a novel Constrained Dual Embedding model, simultaneously embedding and reconciling multiple social networks, to formulate this problem into a unified optimization. To address this optimization, we then design an effective NS-Alternating algorithm and prove it converges to KKT points. To further speed up MASTER, we propose a scalable framework, namely MASTER+. The core idea is to group accounts into clusters and then perform MASTER in each cluster in parallel. Specifically, we design an efficient Augmented Pre-Embedding model and Balance-aware Fuzzy Clustering algorithm for the high efficiency and the high accuracy. Extensive experiments demonstrate that both MASTER and MASTER+ outperform the state-of-the-art approaches. Moreover, MASTER+ inherits the effectiveness of MASTER and enjoys higher efficiency.

Multi-passage machine reading comprehension (MRC) aims to answer a question by multiple passages. Existing multi-passage MRC approaches have shown that employing passages with and without golden answers (i.e. labeled and unlabeled passages) for model training can improve prediction accuracy. In this paper, we present MG-MRC, a novel approach for multi-passage MRC via multi-task learning with generative adversarial training. MG-MRC adopts the extract-then-select framework, where an extractor is first used to predict answer candidates, then a selector is used to choose the final answer. In MG-MRC, we adopt multi-task learning to train the extractor by using both labeled and unlabeled passages. In particular, we use labeled passages to train the extractor by supervised learning, while using unlabeled passages to train the extractor by generative adversarial training, where the extractor is regarded as the generator and a discriminator is introduced to evaluate the generated answer candidates. Moreover, to train the extractor by backpropagation in the generative adversarial training process, we propose a hybrid method which combines boundary-based and content-based extracting methods to produce the answer candidate set and its representation. The experimental results on three open-domain QA datasets confirm the effectiveness of our approach.

User profiling has very important applications for many downstream tasks, such as recommender system, behavior prediction and market strategy. Most existing methods only focus on modeling user profiles of one social network with plenty of data. However, user profiles are difficult to acquire, especially when the data is scarce. Modeling user profiles under such conditions often leads to poor performance. Fortunately, we observed that not only user attributes but also user relationships are useful for user profiling and benefit the results. Meanwhile, similar users have similar behavior in different social networks. Finding user dependencies between social networks will help to infer user profiles. Motivated by such observations, in this paper, we for the first time propose to study the user profiling problem from the transfer learning perspective. We design an efficient User Profile transferring acrOss Networks (UPON) framework, which transfers knowledge of user relationship from one social network with plenty of data to facilitate the user profiling on the other social network with scarce data. In UPON, we first design a novel graph convolutional networks based characteristic-aware domain attention model (GCN-CDAM) to find user dependencies within and between domains (referring to social networks). We then design a dual-domain weighted adversarial learning method to solve the domain shift problem existing in the transferring procedure. Experimental results on Twitter-Foursquare dataset demonstrate that UPON outperforms the state-of-the-art models.

Multi-modality fusion technologies have greatly improved the performance of neural network-based Video Description/Caption, Visual Question Answering (VQA) and Audio Visual Scene-aware Dialog (AVSD) over the recent years. Most previous approaches only explore the last layers of multiple layer feature fusion while omitting the importance of intermediate layers. To solve the issue for the intermediate layers, we propose an efficient Quaternion Block Network (QBN) to learn interaction not only for the last layer but also for all intermediate layers simultaneously. In our proposed QBN, we use the holistic text features to guide the update of visual features. In the meantime, Hamilton quaternion products can efficiently perform information flow from higher layers to lower layers for both visual and text modalities. The evaluation results show our QBN improve the performance on VQA 2.0, furthermore surpasses the approach using large scale BERT or visual BERT pre-trained models. Extensive ablation study has been carried out to examine the influence of each proposed module in this study.

Social network alignment shows fundamental importance in a wide spectrum of applications. To the best of our knowledge, existing studies mainly focus on network alignment at the individual user level, requiring abundant common information between shared individual users. For the networks that cannot meet such requirements, social community structures actually provide complementary and critical information at a slightly coarse-grained level, alignment of which will provide additional information for user alignment. In turn, user alignment also reveals more clues for community alignment. Hence, in this paper, we introduce the problem of joint social network alignment, which aims to align users and communities across social networks simultaneously. Key challenges lie in that (1) how to learn the representations of both users and communities, and (2) how to make user alignment and community alignment benefit from each other. To address these challenges, we first elaborate on the characteristics of real-world networks with the notion of δ-hyperbolicity, and show the superiority of hyperbolic space for representing social networks. Then, we present a novel hyperbolic embedding approach for the joint social network alignment, referred to as Perfect, in a unified optimization. Extensive experiments on real-world datasets show the superiority of Perfect in both user alignment and community alignment.

Recently, aligning users among different social networks has received significant attention. However, most of the existing studies do not consider users’ behavior information during the aligning procedure and thus still suffer from the poor learning performance. In fact, we observe that social network alignment and behavior analysis can benefit from each other. Motivated by such an observation, we propose to jointly study the social network alignment problem and user behavior analysis problem. We design a novel end-to-end framework named BANANA. In this framework, to leverage behavior analysis for social network alignment at the distribution level, we design an earth mover’s distance based alignment model to fuse users’ behavior information for more comprehensive user representations. To further leverage social network alignment for behavior analysis, in turn, we design a temporal graph neural network model to fuse behavior information in different social networks based on the alignment result. Two models above can work together in an end-to-end manner. Through extensive experiments on real-world datasets, we demonstrate that our proposed approach outperforms the state-of-the-art methods in the social network alignment task and the user behavior analysis task, respectively.

In this paper, we tackle the problem of answering multi-dimensional range queries under local differential privacy. There are three key technical challenges: capturing the correlations among attributes, avoiding the curse of dimensionality, and dealing with the large domains of attributes. None of the existing approaches satisfactorily deals with all three challenges. Overcoming these three challenges, we first propose an approach called Two-Dimensional Grids (TDG). Its main idea is to carefully use binning to partition the two-dimensional (2-D) domains of all attribute pairs into 2-D grids that can answer all 2-D range queries and then estimate the answer of a higher dimensional range query from the answers of the associated 2-D range queries. However, in order to reduce errors due to noises, coarse granularities are needed for each attribute in 2-D grids, losing fine-grained distribution information for individual attributes. To correct this deficiency, we further propose Hybrid-Dimensional Grids (HDG), which also introduces 1-D grids to capture finer-grained information on distribution of each individual attribute and combines information from 1-D and 2-D grids to answer range queries. To make HDG consistently effective, we provide a guideline for properly choosing granularities of grids based on an analysis of how different sources of errors are impacted by these choices. Extensive experiments conducted on real and synthetic datasets show that HDG can give a significant improvement over the existing approaches.

In this paper, we study the problem of publishing high-dimensional data in a distributed multi-party environment under differential privacy. In particular, with the assistance of a semi-trusted curator, the parties (i.e., local data owners) collectively generate a synthetic integrated dataset while satisfying ε-differential privacy. To solve this problem, we present a differentially private sequential update of Bayesian network (DP-SUBN) approach. In DP-SUBN, the parties and the curator collaboratively identify the Bayesian network N that best fits the integrated dataset in a sequential manner, from which a synthetic dataset can then be generated. The fundamental advantage of adopting the sequential update manner is that the parties can treat the intermediate results provided by previous parties as their prior knowledge to direct how to learn N. The core of DP-SUBN is the construction of the search frontier, which can be seen as a priori knowledge to guide the parties to update N. By exploiting the correlations of attribute pairs, we propose exact and heuristic methods to construct the search frontier. In particular, to privately quantify the correlations of attribute pairs without introducing too much noise, we first put forward a non-overlapping covering design (NOCD) method, and then devise a dynamic programming method for determining the optimal parameters used in NOCD. Through privacy analysis, we show that DP-SUBN satisfies ε-differential privacy. Extensive experiments on real datasets demonstrate that DP-SUBN offers desirable data utility with low communication cost.

Language model (LM) plays an important role in natural language processing (NLP) systems, such as machine translation, speech recognition, learning token embeddings, natural language generation, and text classification. Recently, the multilayer long short-term memory (LSTM) models have been demonstrated to achieve promising performance on word-level language modeling. For each LSTM layer, larger hidden size usually means more diverse semantic features, which enables the LM to perform better. However, we have observed that when a certain LSTM layer reaches a sufficiently large scale, the promotion of overall effect will slow down, as its hidden size increases. In this article, we analyze that an important factor leading to this phenomenon is the high correlation between the newly extended hidden states and the original hidden states, which hinders diverse feature expression of the LSTM. As a result, when the scale is large enough, simply lengthening the LSTM hidden states will cost tremendous extra parameters but has little effect. We propose a simple yet effective improvement on each LSTM layer consisting of a large-scale Major LSTM and a small-scale Minor LSTM to break the high correlation between the two parts of hidden states, which we call Major-Minor LSTMs (MMLSTMs). In experiments, we demonstrate the LM with MMLSTMs surpasses the existing state-of-the-art model on Penn Treebank (PTB) and WikiText-2 (WT2) data sets and outperforms the baseline by 3.3 points in perplexity on WikiText-103 data set without increasing model parameter counts.

Software-defined networking controllers use the OpenFlow discovery protocol (OFDP) to collect network topology status. The OFDP detects the link between switches by generating link layer discovery protocol (LLDP) packets. However, OFDP is not a security protocol. Attackers can use it to perform topology discovery via injection, man-in-the-middle, and flooding attacks to confuse the network topology. This study proposes a correlation-based topology anomaly detection mechanism. Spearman’s rank correlation is used to analyze the network traffic between links and measure the round-trip time of each LLDP frame to determine whether a topology discovery via man-in-the-middle attack exists. This study also adds a dynamic authentication key and counting mechanism in the LLDP frame to prevent attackers from using topology discovery via injection attack to generate fake links and topology discovery via flooding attack to cause network routing or switching abnormalities.

Social network alignment, identifying social accounts of the same individual across different social networks, shows fundamental importance across a wide spectrum of applications. Individuals more often than not join in multiple social networks and it is in fact intractable or even impossible to acquiring supervision for guiding the alignment. However, to the best of our knowledge, none of existing methods can align multiple social networks without supervision. In this paper, we propose to study the problem of unsupervised multiple social network alignment. To address this problem, we propose a novel unsupervised model of Matrix factorization with diagonal Cone under orthogonal Constraint, referred to as MC2. Its core idea is to embed and align multiple social networks in the common subspace via an unsupervised approach. Specifically, in MC2model, we first design a matrix optimization to infer the common subspace from different social networks. To address the nonconvex optimization, we then design an efficient alternating algorithm by leveraging its inherent functional property. Through extensive experiments on real-world datasets, we demonstrate that the proposed MC2model significantly outperforms the state-of-the-art methods.

Social network alignment, aligning different social networks on their common users, is receiving dramatic attention from both academic and industry. All existing studies consider the social network to be static and neglect its inherent dynamics. In fact, the dynamics of social networks contain the discriminative pattern of an individual, which can be leveraged to facilitate social network alignment. Hence, we for the first time propose to study the problem of aligning dynamic social networks. Towards this end, we propose a novel Dynamic social Network Alignment (DNA) framework, a unified optimization approach over deep neural architectures, to unfold the fruitful dynamics to perform alignment. However, it faces tremendous challenges in both modeling and optimization: (1) To model the intra-network dynamics, we explore the local dynamics of the latent pattern in friending evolvement and the global consistency of the representation similarity with neighbors. We design a novel deep neural architecture to obtain the dual embedding capturing local dynamics and global consistency for each user. (2) To model the inter-network alignment, we exploit the underlying identity of an individual from the dual embedding in each dynamic social network. We design a unified optimization approach interplaying proposed deep neural architectures to construct a common subspace of identity embeddings. (3) To address this optimization problem, we design an effective alternating algorithm with solid theoretical guarantees. We conduct extensive experiments on real-world datasets and show that the proposed DNA framework substantially outperforms the state-of-the-art methods.

In social networks, one of the most significant challenges is how to estimate the tweet popularity. Prior studies about this problem focus on leveraging different aspects of just a single tweet, while ignoring the impact of historical tweets. In this paper, we propose to leverage such historical information and rethink the problem of tweet popularity estimation. From historical information, there are two important factors that can be extracted: (1) user reputation feature, which can represent coarse-grained level of tweet popularity; (2) tweet related features, which can represent fine-grained level of tweet popularity. To incorporate two factors from historical information, we design a novel deep neural architecture, a Bi-layered LSTM for tweet popularity Estimation, called DeepBlue. Specifically, we first propose a user-reputation aware mechanism to combine coarse-grained and fine-grained level estimation into a unified LSTM model. We then propose a time aware mechanism to address the time interval irregularity issue in standard LSTM. Finally, we apply the Poisson regression model to obtain the overall loss for tweet popularity estimation. Extensive experiments demonstrate the superiority of our proposed approach to other state-of-the-arts in terms of MAE and SRC.

In this paper, we initiate the study of collecting preference rankings under local differential privacy. The key technical challenge comes from the fact that the number of possible rankings increases factorially in the number of items to rank. In practical settings, this number could be large, leading to excessive injected noise. To solve this problem, we present a novel approach called SAFARI. The general idea is to collect a set of distributions over small domains which are carefully chosen based on the riffle independent model to approximate the overall distribution of users' rankings, and then generate a synthetic ranking dataset from the obtained distributions. By working on small domains instead of a large domain, SAFARI can significantly reduce the magnitude of added noise. Extensive experiments on real datasets confirm the effectiveness of SAFARI.

Supervised topic classifiers for Twitter and other media sources are important in a variety of long-term topic tracking tasks. Unfortunately, over long periods of time, features that are predictive during the training period may prove ephemeral and fail to generalize to prediction at future times. For example, if we trained a classifier to identify tweets concerning the topic of “Celebrity Death”, individual celebrity names and terms associated with these celebrities such as “Nelson Mandela” or “South Africa” would prove to be temporally unstable since they would not generalize over long periods of time; in contrast, terms like “RIP” (rest in peace) would prove to be temporally stable predictors of this topic over long periods of time. In this paper, we aim to design supervised learning methods for Twitter topic classifiers that are capable of automatically downweighting temporally unstable features to improve future generalization. To do this, we first begin with an oracular approach that chooses temporally stable features based on knowledge of both train and test data labels. We then search for feature metrics evaluated on only the training data that are capable of recovering the temporally stable features identified by our oracular definition. We next embed the top-performing metric as a temporal stability regularizer in logistic regression with the important property that the overall training objective retains convexity, hence enabling a globally optimal solution. Finally, we train our topic classifiers on 6 Twitter topics over roughly one year of data and evaluate on the following year of data, showing that logistic regression with our temporal stability regularizer generally outperforms logistic regression without such regularization across the full precision-recall continuum. Overall, these results establish a novel regularizer for training long-term temporally stable topic classifiers for Twitter and beyond.

Text classification is a foundational task in many natural language processing applications. All traditional text classifiers take words as the basic units and conduct the pre-training process (like word2vec) to directly generate word vectors at the first step. However, none of them have considered the information contained in word structure which is proved to be helpful for text classification. In this paper, we propose a word-building method based on neural network model that can decompose a Chinese word to a sequence of radicals and learn structure information from these radical level features which is a key difference from the existing models. Then, the convolutional neural network is applied to extract structure information of words from radical sequence to generate a word vector, and the long short-term memory is applied to generate the sentence vector for the prediction purpose. The experimental results show that our model outperforms other existing models on Chinese dataset. Our model is also applicable to English as well where an English word can be decomposed down to character level, which demonstrates the excellent generalisation ability of our model. The experimental results have proved that our model also outperforms others on English dataset.

It has been shown that stock price movements are influenced by news. To predict stock movements with news, many existing works rely only on the news title since the news content may contain irrelevancies which seriously degrade the prediction accuracy. However, we observe that there is still useful information in the content which is not reflected in the title, and simply ignoring the content will result in poor performance. In this paper, taking advantage of neural representation learning, we propose a hierarchical complementary attention network (HCAN) to capture valuable complementary information in news title and content for stock movement prediction. In HCAN, we adopt a two-level attention mechanism to quantify the importances of the words and sentences in a given news. Moreover, we design a novel measurement for calculating the attention weights to avoid capturing redundant information in the news title and content. Experimental results on news datasets show that our proposed model outperforms the state-of-the-art techniques.

In recent years, friending recommendation has played a crucial role on the explosive growth of online social networks. Prior studies on this problem have the following two limitations: i) they assume that there is only one pair of source and target at one time; and ii) the intermediate user can indefinitely forward friending requests. These two assumptions are impractical for online social networks. To bridge this gap, we study how to maximize the acceptance probability for multi-pair active friending in online social networks. In this paper, we first establish a probability model for the Multi-pair Active Friending with Tolerance and then propose two efficient algorithms: Multi-pair Active Friending algorithm for Conflict Resolution (MAFCR) and Group-based Multi-pair Active Friending algorithm for Conflict Resolution (MAFCR-G). Through extensive experiments, we show that the algorithm MAFCR significantly outperforms the baseline algorithm in terms of average acceptance probability, and the algorithm MAFCR-G greatly reduces the running time while obtaining similar average acceptance probability.

Community Question Answering (CQA) has increasingly become an important service for people asking questions and providing answers online, which enables people to help each other by sharing knowledge. Recently, with accumulation of users and contents, much concern has arisen over the efficiency and answer quality of CQA services. To address this problem, question routing has been proposed which aims at routing new questions to suitable answerers, who have both high possibility and high ability to answer the questions. In this paper, we formulate question routing as a multi-objective ranking problem, and present a multi-objective learning-to-rank approach for question routing (MLQR), which can simultaneously optimize the answering possibility and answer quality of routed users. In MLQR, realizing that questions are relatively short and usually attached with tags, we first propose a tagword topic model (TTM) to derive topical representations of questions. Based on TTM, we then develop features for each question-user pair, which are captured at both platform level and thread level. In particular, the platform-level features summarize the information of a user from his/her history posts in the CQA platform, while the thread-level features model the pairwise competitions of a user with others in his/her answered threads. Finally, we extend a state-of-the-art learning-to-rank algorithm for training a multi-objective ranking model. Extensive experimental results on real-world datasets show that our MLQR can outperform state-of-the-art methods in terms of both answering possibility and answer quality.

In this paper, we present an encoder-decoder model for distant supervised relation extraction. Given an entity pair and its sentence bag as input, in the encoder component, we employ the convolutional neural network to extract the features of the sentences in the sentence bag and merge them into a bag representation. In the decoder component, we utilize the long short-term memory network to model relation dependencies and predict the target relations in a sequential manner. In particular, to enable the sequential prediction of relations, we introduce a measure to quantify the amounts of information the relations take in their sentence bag, and use such information to determine the order of the relations of a sentence bag during model training. Moreover, we incorporate the attention mechanism into our model to dynamically adjust the bag representation to reduce the impact of sentences whose corresponding relations have been predicted. Extensive experiments on a popular dataset show that our model achieves significant improvement over state-of-the-art methods.

Recently, reconciling social networks receives significant attention. Most of the existing studies have limitations in the following three aspects: multiplicity, comprehensiveness and robustness. To address these three limitations, we rethink this problem and propose the MASTER framework, i.e., across Multiple social networks, integrate Attribute and STructure Embedding for Reconciliation. In this framework, we first design a novel Constrained Dual Embedding model by simultaneously embedding and reconciling multiple social networks to formulate our problem into a unified optimization. To address this optimization, we then design an effective algorithm called NS-Alternating. We also prove that this algorithm converges to KKT points. Through extensive experiments on real-world datasets, we demonstrate that MASTER outperforms the state-of-the-art approaches.

In this paper, we study the location‐aware targeted influence maximization problem in social networks, which finds a seed set to maximize the influence spread over the targeted users. In particular, we consider those users who have both topic and geographical preferences on promotion products as targeted users. To efficiently solve this problem, one challenge is how to find the targeted users and compute their preferences efficiently for given requests. To address this challenge, we devise a TR‐tree index structure, where each tree node stores users' topic and geographical preferences. By traversing the TR‐tree in depth‐first order, we can efficiently find the targeted users. Another challenge of the problem is to devise algorithms for efficient seeds selection. We solve this challenge from two complementary directions. In one direction, we adopt the maximum influence arborescence (MIA) model to approximate the influence spread, and propose two efficient approximation algorithms with approximation ratio, which prune some candidate seeds with small influences by precomputing users' initial influences offline and estimating the upper bound of their marginal influences online. In the other direction, we propose a fast heuristic algorithm to improve efficiency. Experiments conducted on real‐world data sets demonstrate the effectiveness and efficiency of our proposed algorithms.

Mining frequent subgraphs from a collection of input graphs is an important task for exploratory data analysis on graph data. However, if the input graphs contain sensitive information, releasing discovered frequent subgraphs may pose considerable threats to individual privacy. In this paper, we study the problem of frequent subgraph mining (FSM) under the rigorous differential privacy model. We present a two-phase differentially private FSM algorithm, which is referred to as DFG. In DFG, frequent subgraphs are privately identified in the first phase, and the noisy support of each identified frequent subgraph is calculated in the second phase. In particular, to privately identity frequent subgraphs, we propose a frequent subgraph identification approach, which can improve the accuracy of discovered frequent subgraphs through candidate pruning. Moreover, to compute the noisy support of each identified frequent subgraph, we devise a lattice-based noisy support computation approach, which leverages the inclusion relations between the discovered frequent subgraphs to improve the accuracy of the noisy supports. Through formal privacy analysis, we prove that DFG satisfies ε-differential privacy. Extensive experimental results on real datasets show that DFG can privately find frequent subgraphs while achieving high data utility.

With the rapid development of location-based services in mobile Internet, spatial keyword queries have been widely employed in various real-life applications in recent years. To realize the great flexibility and cost savings, more and more data owners are motivated to outsource their spatio-textual data services to the cloud. However, directly outsourcing such services to the untrusted cloud may arise serious privacy concerns. In this paper, we study the privacy-preserving top-$k$spatial keyword query problem in untrusted cloud environments. Existing studies primarily focus on the design of privacy-preserving schemes for either spatial or keyword queries, and they cannot be applied to solve the privacy-preserving spatial keyword query problem. To address this problem, we present a novel privacy-preserving top-$k$spatial keyword query scheme. In particular, we build an encrypted tree index to facilitate privacy-preserving top-$k$spatial keyword queries, where spatial and textual data are encrypted in a unified way. To search with the encrypted tree index, we propose two effective techniques for the similarity computations between queries and tree nodes under encryption. To improve query performance on large-scale spatio-textual data, we further propose a keyword-based secure pruning method. Thorough analysis shows the validity and security of our scheme. Extensive experimental results on real datasets demonstrate our scheme achieves high efficiency and good scalability.

With the development of large-scale knowledge bases, people are building systems which give simple answers to questions based on consolidate facts. In this paper, we focus on simple questions, which ask about only a subject and relation in the knowledge base. Observing that certain parts of a question usually overlap with names of its corresponding subject and relation in the knowledge base, we argue that a question is formed by a mixture of copying and generation. To model that, we propose a sequence-to-sequence (seq2seq) architecture which encodes a candidate subject-relation pair and decodes it into the given question, where the decoding probability is used to select the best candidate. In our decoder, the copying mode points the subject or relation and duplicates its name, while the generating mode summarizes the meaning of the subject-relation pair and produces a word to smooth the question. Realizing that although sometimes a subject or relation is pointed, different names or keywords might be used, we also incorporate a paraphrasing mode to supplement the copying mode using an automatically mined lexicon. Extensive experiments on the largest dataset exhibit our better performance compared with the state-of-the-art methods.

Hashing has attracted broad research interests in large scale image retrieval due to its high search speed and efficient storage. Recently, many deep hashing methods have been proposed to perform simultaneous nonlinear feature learning and hash projection learning, which have shown superior performance compared to hand-crafted feature based hashing methods. Nonlinear projection functions have shown their advantages over the linear ones due to their powerful generalization capabilities. To improve the performance of deep hashing methods by generalizing projection functions, we propose the idea of implementing a pure nonlinear deep hashing network architecture. By consolidating the above idea, this paper presents a Deep Supervised Hashing architecture with Nonlinear Projections (DSHNP). In particular, soft decision trees are adopted as the nonlinear projection functions, since they can generate differentiable nonlinear outputs and can be trained with deep neural networks in an end-to-end way. Moreover, to make the hash codes as independent as possible, we design two regularizers imposed on the parameter matrices of the leaves in the soft decision trees. Extensive evaluations on two benchmark image datasets show that the proposed DSHNP outperforms several state-of-the-art hashing methods.

Abstract The rapid growth of event‐based social networks (EBSNs) has generated great demand for personalized event recommendation. Indeed, new events are published every day in EBSNs. In this paper, we focus on the problem of recommending new events (i.e., the newly published events that have not yet received any user response) to registered users in EBSNs. Notice that collaborative filtering is ineffective for recommending new events due to the short lifetime of events and the lack of historical information, that is, the cold‐start problem. A straightforward approach to address this problem is to adopt content‐based recommendation techniques, for example, deriving user interests through the content information of the events they attended. Nevertheless, we observe that organizer influence and geographical preference also play important roles in a user's decision to participate in an event. Motivated by this observation, we combine user interest, organizer influence, and geographical preference to present a unified model for new event recommendation. In particular, we utilize a topic model to derive user interests while adopting matrix factorization to infer organizer influences on users from the interactions between users and organizers. Moreover, we model users' geographical preferences via their location histories of attended events. We conduct a performance evaluation using real‐world data collected from DoubanEvent. The experimental results demonstrate the effectiveness of our proposed recommendation model.

Location-aware publish/subscribe is an important location-based service based on server-initiated model. Often times, the owner of massive spatio-textual messages and subscriptions outsources its location-aware publish/subscribe services to a third-party service provider, for example, cloud service provider, who is responsible for delivering messages to their relevant subscribers. The issue arising here is that the messages delivered by the service provider might be tailored for profit purposes, intentionally or not. Therefore, it is essential to develop mechanisms which allow subscribers to verify the correctness of the messages delivered by the service provider. In this paper, we study the problem of authenticating messages in outsourced location-aware publish/subscribe services. We propose an authenticated framework which not only can deliver the messages efficiently but also can make the subscribers’ authentication available with low cost. Extensive experiments on a real-world dataset demonstrate the effectiveness and efficiency of our proposed authenticated framework.

Community Question Answering (CQA) has increasingly become an important service for people asking questions and providing answers online, which enables people to help each other by sharing knowledge. Recently, with accumulation of users and contents, much concern has arisen over the efficiency and answer quality of CQA services. To address this problem, question routing has been proposed which aims at routing new questions to suitable answerers, who have both high possibility and high ability to answer the questions. In this paper, we formulate question routing as a multi-objective ranking problem, and present a multi-objective learning-to-rank approach for question routing (MLQR), which can simultaneously optimize the answering possibility and answer quality of routed users. In MLQR, realizing that questions are relatively short and usually attached with tags, we first propose a tagword topic model (TTM) to derive topical representations of questions. Based on TTM, we then develop features for each question-user pair, which are captured at both platform level and thread level. In particular, the platform-level features summarize the information of a user from his/her history posts in the CQA platform, while the thread-level features model the pairwise competitions of a user with others in his/her answered threads. Finally, we extend a state-of-the-art learning-to-rank algorithm for training a multi-objective ranking model. Extensive experimental results on real-world datasets show that our MLQR can outperform state-of-the-art methods in terms of both answering possibility and answer quality.

This paper studies the problem of identifying influencers on specific topics in the microblog sphere. Prior works usually use the cumulative number of social links to measure users' topic-level influence, which ignores the dynamics of influence. As a result, they usually find faded influencers. To address the limitations of prior methods, we propose a novel probabilistic generative model to capture the variation of influence over time. Then a influence decay method is proposed to measure users' current topic-level influence.

In network virtualization, one of the key problems is to embed a sequence of virtual networks with both node and link constraints onto the physical network, which is known to be NP-hard. When a virtual network arrives, the recent studies focus on designing a solution to minimize the energy cost while maximizing the revenue of the physical network at that time. However, after some time, due to the significant dynamics of the resources of the physical network, the previous solution may become less energy efficient. In this paper, we take a further step and study how to re-optimize the energy cost by leveraging the migration technique. In particular, we first model the pros (e.g., energy saving) and cons (e.g., interruption time and bandwidth waste) of migration. Then we design a heuristic energy aware virtual network migration algorithm called EA-VNM. It answers the following key questions: when performing migration, migrate which virtual nodes to where, and how to perform migration. Extensive simulations show that our algorithm significantly reduces the energy cost by up to 25% over the state-of-the-art algorithm while maintaining similar revenue.

In this paper, we study the novel problem of publishing high-dimensional data in a distributed multi-party environment under differential privacy. In particular, with the assistance of a semi-trusted curator, the involved parties (i.e., local data owners) collectively generate a synthetic integrated dataset while satisfying ε-differential privacy for any local dataset. To solve this problem, we present a differentially private sequential update of Bayesian network (DP-SUBN) solution. In DP-SUBN, the parties and the curator collaboratively identify the Bayesian network ℕ that best fits the integrated dataset D in a sequential manner, from which a synthetic dataset can then be generated. The fundamental advantage of adopting the sequential update manner is that the parties can treat the statistical results provided by previous parties as their prior knowledge to direct how to learn ℕ. The core of DP-SUBN is the construction of the search frontier, which can be seen as a priori knowledge to guide the parties to update ℕ. To improve the fitness of ℕ and reduce the communication cost, we introduce a correlation-aware search frontier construction (CSFC) approach, where attribute pairs with strong correlations are used to construct the search frontier. In particular, to privately quantify the correlations of attribute pairs without introducing too much noise, we first propose a non-overlapping covering design (NOCD) method, and then introduce a dynamic programming method to find the optimal parameters used in NOCD to ensure that the injected noise is minimum. Through formal privacy analysis, we show that DP-SUBN satisfies ε-differential privacy for any local dataset. Extensive experiments on a real dataset demonstrate that DP-SUBN offers desirable data utility with low communication cost.

Frequent itemset mining (FIM) is one of the most fundamental problems in data mining. It has practical importance in a wide range of application areas such as decision support, Web usage mining, bioinformatics, etc. Given a database, where each transaction contains a set of items, FIM tries to find itemsets that occur in transactions more frequently than a given threshold. Despite valuable insights the discovery of frequent itemsets can potentially provide, if the data is sensitive (e.g., web browsing history and medical records), releasing the discovered frequent itemsets might pose considerable threats to individual privacy.

Mining frequent subgraphs from a collection of input graphs is an important topic in data mining research. However, if the input graphs contain sensitive information, releasing frequent subgraphs may pose considerable threats to individual's privacy. In this paper, we study the problem of frequent subgraph mining (FGM) under the rigorous differential privacy model. We introduce a novel differentially private FGM algorithm, which is referred to as DFG. In this algorithm, we first privately identify frequent subgraphs from input graphs, and then compute the noisy support of each identified frequent subgraph. In particular, to privately identify frequent subgraphs, we present a frequent subgraph identification approach which can improve the utility of frequent subgraph identifications through candidates pruning. Moreover, to compute the noisy support of each identified frequent subgraph, we devise a lattice-based noisy support derivation approach, where a series of methods has been proposed to improve the accuracy of the noisy supports. Through formal privacy analysis, we prove that our DFG algorithm satisfies ε-differential privacy. Extensive experimental results on real datasets show that the DFG algorithm can privately find frequent subgraphs with high data utility.

A spatio-textual similarity join searches a spatio-textual data collection and reports the object pairs that satisfy the specified spatial distance threshold and textual similarity threshold. However, when the data owner outsources the join computations to a third-party cloud service provider, the service provider may send incomplete or incorrect join results to the data owner. In this paper, we propose a pairwise authentication scheme, a cluster based scheme and an order and bound based scheme to authenticate the results of spatiotextual similarity joins. Extensive experiments on a real-world dataset verify the effectiveness and efficiency of our proposed schemes in terms of various performance metrics.

Abstract In this paper, we study the problem of authentication of spatio‐textual similarity join queries in untrusted cloud environments. To solve this problem, we first propose a pairwise authentication scheme, where object pairs are considered as basic processing units. In this scheme, an object hash tree is proposed for the data owner (DO) to build the authenticated data structure (ADS) over the data collection. Moreover, during join processing, a pair table is introduced for the service provider (SP) to construct the verification object (VO) for client's authentication. However, when clients authenticate the join results, they have large number of pairs to examine, which leads to excessive computation cost. Therefore, we then propose an optimized MR*‐tree‐based scheme. In this scheme, the DO spatially organizes the objects in an ADS called MR*‐tree, which combines the concepts of the Merkle hash tree and the R*‐tree. Based on the MR*‐tree, the SP employs the depth‐first search strategy to find the join results and constructs the VO according to the visited nodes of the MR*‐tree. Our extensive experiments on the real‐world dataset verify the effectiveness and efficiency of our proposed schemes on several performance metrics, including the data preprocessing time, running time, VO size, and authentication time. Copyright © 2016 John Wiley & Sons, Ltd.

In this paper, we study the problem of mining frequent sequences under the rigorous differential privacy model. We explore the possibility of designing a differentially private frequent sequence mining (FSM) algorithm which can achieve both high data utility and a high degree of privacy. We found, in differentially private FSM, the amount of required noise is proportionate to the number of candidate sequences. If we could effectively prune those unpromising candidate sequences, the utility and privacy tradeoff can be significantly improved. To this end, by leveraging a sampling-based candidate pruning technique, we proposePFS$^2$, a novel differentially private FSM algorithm. It is the first algorithm that supports the general gap-constrained FSM in the context of differential privacy. The gap constraints in FSM can be used to limit the mining results to a controlled set of frequent sequences. In ourPFS$^2$algorithm, the core is to utilize sample databases to prune the candidate sequences generated based on the downward closure property. In particular, we use the noisy local support of candidate sequences in the sample databases to estimate which candidate sequences are potentially frequent. To improve the accuracy of such private estimations, a gap-aware sequence shrinking method is proposed to enforce the length constraint on the sample databases. Moreover, to calibrate the amount of noise required by differential privacy, a gap-aware sensitivity computation method is proposed to obtain the sensitivity of the local support computations with different gap constraints. Furthermore, to decrease the probability of misestimating frequent sequences as infrequent, a threshold relaxation method is proposed to relax the user-specified threshold for the sample databases. Through formal privacy analysis, we show that ourPFS$^2$algorithm is$\epsilon$-differentially private. Extensive experiments on real datasets illustrate that ourPFS$^2$algorithm can privately find frequent sequences with high accuracy.

In network virtualization, how to efficiently embed virtual networks with both node and link demands into a shared physical network, namely virtual network embedding, has attracted significant attention. Most of prior studies on this problem have the following two limitations: i) they assumed that the virtual network demands are constant values, which does not hold in real-world network since such demands may vary a lot over time; ii) their primary goal was to generate more revenues for the physical network, with no consideration of the energy cost, which has become a critical issue for the physical network. In this paper, we bridge the gap and study the energy aware virtual network embedding with dynamic demands. Specifically, we first model the dynamics of virtual network demands as a combination of following Gaussian distribution and exhibiting daily diurnal pattern. We then design an efficient heuristic algorithm by leveraging the dynamic characteristic of virtual network demands to minimize the energy consumption while keeping high revenue for the physical network. We implemented our algorithm in C++ and performed side-by-side comparison with prior algorithm. Extensive simulations show that our algorithm can significantly reduce the energy cost by up to 16% over the state-of-the-art algorithm, while maintaining near the same revenue.

In this paper, we study the problem of mining frequent sequences under the rigorous differential privacy model. We explore the possibility of designing a differentially private frequent sequence mining (FSM) algorithm which can achieve both high data utility and a high degree of privacy. We found, in differentially private FSM, the amount of required noise is proportionate to the number of candidate sequences. If we could effectively reduce the number of unpromising candidate sequences, the utility and privacy tradeoff can be significantly improved. To this end, by leveraging a sampling-based candidate pruning technique, we propose a novel differentially private FSM algorithm, which is referred to as PFS2. The core of our algorithm is to utilize sample databases to further prune the candidate sequences generated based on the downward closure property. In particular, we use the noisy local support of candidate sequences in the sample databases to estimate which sequences are potentially frequent. To improve the accuracy of such private estimations, a sequence shrinking method is proposed to enforce the length constraint on the sample databases. Moreover, to decrease the probability of misestimating frequent sequences as infrequent, a threshold relaxation method is proposed to relax the user-specified threshold for the sample databases. Through formal privacy analysis, we show that our PFS2algorithm is ϵ-differentially private. Extensive experiments on real datasets illustrate that our PFS2algorithm can privately find frequent sequences with high accuracy.

This paper studies the problem of energy-efficient scheduling for parallel tasks in high-performance computing systems, such as clusters and data centers. Our goal is to minimize the energy consumption of parallel tasks within a deadline constraint. Among the existing techniques that reduce the energy for computing systems, dynamic voltage and frequency scaling (DVFS) is generally considered as a promising technique that can strike a balance between the energy consumption and the performance for tasks. By using the DVFS technique, the main line of research is to slack the non-critical path tasks to reduce energy consumption of parallel tasks. However, the existing studies slack the tasks greedily and could not efficiently utilize the slack-room, i.e. the idle time of the processors. In this paper, we develop a novel slacking concept, partial optimal slacking (POS), which can take full advantage of the slack-room by slack-sharing. Our formal analysis shows that POS can lead to optimum energy reduction in the partial task set. Based on the POS concept, we propose a new scheduling algorithm for parallel tasks, namely enhanced an energy-efficient scheduling (EES) algorithm. Through extensive evaluation studies, the results demonstrate that the EES algorithm can further improve the energy efficiency of parallel tasks while meeting the deadline constraint.

With rapid advances in wireless communication, mobile devices and positioning technologies, location-based services (LBS) have recently emerged as one of today's most important applications in mobile networks. To obtain great flexibility and cost savings, LBS providers may outsource their data services to the cloud. However, to protect data privacy, sensitive data have to be encrypted before outsourcing, which may impede the functionality and performance of the data services. In this paper, to make one step closer towards practical deployment of LBS in the cloud, we study the problem of secure and efficient k-nearest neighbor (kNN) query processing over encrypted spatial data. Although there exist a number of studies on kNN query processing over encrypted data, few of them can provide security and efficiency simultaneously. To this end, we present a secure and efficient kNN query (SEkQ) scheme. In this scheme, a new encryption method, namely, asymmetric scalar-product-preserving encryption with Laplace noise (ASPELN) is proposed, which can resist both the chosen-plaintext and known-plaintext attacks. Based on ASPELN, an encrypted hierarchical index called SR-tree (short for Secure R-tree) is devised to facilitate efficient kNN query processing on encrypted spatial data. To search with the SR-tree index, two effective methods, namely, anchor-assisted position determination and position-distinguished trapdoor generation are proposed for the distance computations between the query point and SR-tree nodes under encryption. Thorough analysis shows the validity and security of the proposed scheme. Extensive experimental results on real datasets further demonstrate the proposed scheme can achieve high efficiency and good scalability. Copyright © 2015 John Wiley & Sons, Ltd.

Abstract Communication systems utilize the distributed hash table (DHT) approach to build the network infrastructure for advantages of even distribution of workload, high scalability, and cost‐effectiveness. Although DHT is undoubtedly applicative in such architectures, some practical distinctions still should be considered to meet the performance requirements of communication infrastructures. This paper focuses on two features of the distributed communication system, the real‐time response and dynamic network maintenance, and proposes the Comb, which is a hierarchical DHT lookup service. Comb's overlay is organized as a two‐layered architecture, workload is distributed evenly among nodes, and most queries can be routed in no more than two hops. Comb is capable to scale to large systems and resilient to fluctuate, it provides a self‐managing and self‐healing mechanism for supporting system recovery from inconsistence. Comb performs effectively with low bandwidth consumption and satisfactory fault tolerance even in a continuously changing environment. Both theoretical analyses and experimental results demonstrate that the two‐layered architecture of Comb is resilient and efficient. Comb improves the performances on routing delay and lookup failure rates with high scalability and availability. Copyright © 2014 John Wiley & Sons, Ltd.

Co-clustering has emerged to be a powerful data mining tool for two-dimensional co-occurrence and dyadic data. However, co-clustering algorithms often require significant computational resources and have been dismissed as impractical for large data sets. Existing studies have provided strong empirical evidence that expectation-maximization (EM) algorithms (e.g., k-means algorithm) with sequential updates can significantly reduce the computational cost without degrading the resulting solution. Motivated by this observation, we introduce sequential updates for alternate minimization co-clustering (AMCC) algorithms which are variants of EM algorithms, and also show that AMCC algorithms with sequential updates converge. We then propose two approaches to parallelize AMCC algorithms with sequential updates in a distributed environment. Both approaches are proved to maintain the convergence properties of AMCC algorithms. Based on these two approaches, we present a new distributed framework, Co-ClusterD, which supports efficient implementations of AMCC algorithms with sequential updates. We design and implement Co-ClusterD, and show its efficiency through two AMCC algorithms: fast nonnegative matrix tri-factorization (FNMTF) and information theoretic co-clustering (ITCC). We evaluate our framework on both a local cluster of machines and the Amazon EC2 cloud. Empirical results show that AMCC algorithms implemented in Co-ClusterD can achieve a much faster convergence and often obtain better results than their traditional concurrent counterparts.

Recently, there has been a growing interest in designing differentially private data mining algorithms. Frequent itemset mining (FIM) is one of the most fundamental problems in data mining. In this paper, we explore the possibility of designing a differentially private FIM algorithm which can not only achieve high data utility and a high degree of privacy, but also offer high time efficiency. To this end, we propose a differentially private FIM algorithm based on the FP-growth algorithm, which is referred to as PFP-growth. The PFP-growth algorithm consists of a preprocessing phase and a mining phase. In the preprocessing phase, to improve the utility and privacy tradeoff, a novel smart splitting method is proposed to transform the database. For a given database, the preprocessing phase needs to be performed only once. In the mining phase, to offset the information loss caused by transaction splitting, we devise a run-time estimation method to estimate the actual support of itemsets in the original database. In addition, by leveraging the downward closure property, we put forward a dynamic reduction method to dynamically reduce the amount of noise added to guarantee privacy during the mining process. Through formal privacy analysis, we show that our PFP-growth algorithm is ε-differentially private. Extensive experiments on real datasets illustrate that our PFP-growth algorithm substantially outperforms the state-of-the-art techniques.

PaaS is known as an application engine which third party developers can deploy their application onto. Security of PaaS becomes important as applications shares resources. How to secure and isolation the resources become an important topic. In this paper, a security PaaS container is proposed which is based on a customized JVM. This container is fully implemented and evaluated in real setting.

Storm has emerged as a promising computation platform for stream data processing. In this paper, we first show inefficiencies of the current practice of Storm scheduling and challenges associated with applying traffic-aware online scheduling in Storm via experimental results and analysis. Motivated by our observations, we design and implement a new stream data processing system based on Storm, namely, T-Storm. Compared to Storm, T-Storm has the following desirable features: 1) based on runtime states, it accelerates data processing by leveraging effective traffic-aware scheduling for assigning/re-assigning tasks dynamically, which minimizes inter-node and inter-process traffic while ensuring no worker nodes are overloaded, 2) it enables fine-grained control over worker node consolidation such that T-Storm can achieve better performance with even fewer worker nodes, 3) it allows hot-swapping of scheduling algorithms and adjustment of scheduling parameters on the fly, and 4) it is transparent to Storm users (i.e., Storm applications can be ported to run on T-Storm without any changes). We conducted real experiments in a cluster using well-known data processing applications for performance evaluation. Extensive experimental results show that compared to Storm (with the default scheduler), T-Storm can achieve over 84% and 27% speedup on lightly and heavily loaded topologies respectively (in terms of average processing time) with 30% less number of worker nodes.

Saving power on base stations (BS) becomes a critical issue in wireless cellular networks. Many existing work has proposed to schedule BS into sleep to save energy. However, in reality, it is very difficult to shut down and reboot BSs frequently due to numerous technical issues and performance requirements. In this work, we propose a much more practical solution and offer a new perspective on implementing Green Wireless Networking by embracing the hot-trended small cell network idea. Instead of putting BSs into sleep, we tactically reduce the coverage (and the power usage) of each BS, and strategically place microcells (relay stations) to offload the traffic transmitted to/from BSs in order to save total power consumption. We propose approximation algorithms for various network design scenarios, with different wireless network setups and different power saving optimization objectives. Extensive numerical results are presented to confirm our theoretical analysis.

Abstract Denial‐of‐Service attacks continue to plague the Internet. Tracing an individual attack packet to its origin is an important step in defending against these attacks. For this reason, researchers have proposed several approaches for single‐packet IP traceback. Packet logging is a generic technique in these methods, which results in the high overhead at routers and low traceback accuracy. In this paper, we propose a novel path‐based approach for single‐packet IP traceback. Our approach makes use of the routing paths to set up traceback paths, instead of packet logging, so as to improve single‐packet IP traceback in several dimensions: (i) our storage overhead is only related to the number of routing paths, no matter how many packets traverse on them; (ii) the number of queried routers during the traceback process is only related to the number of hops in the attack path; (iii) the false positives in attack‐path construction can be negligible. We perform extensive mathematical analysis and simulations to evaluate our approach. The results show that our approach represents a step forward in preciseness and efficiency compared with the previous work. Copyright © 2013 John Wiley & Sons, Ltd.

Blocking attack flows to protect the threatened resources is a necessary step in defending against the Distributed Denial-of-Service DDoS attacks. Two kinds of reactive packet filtering technologies have been proposed as close to victim-end filtering and close to source-ends filtering. The first scheme only involves a single Active Filtering Routers AFRs but damages the whole network bandwidth resource; another extreme scheme requires millions of AFRs and thus degrades the network transmission performance, but it has the best defense effect. A feasible scheme should use a certain quantity of AFRs to filter attack flows between the victim end and the source ends. Going one step further, in this paper, we make the first effort on studying the filtering location to maximize the protected network bandwidth while not permitting any attack flow to reach the victim. We formulate this problem to an integer linear programming problem and design an efficient heuristic filtering location algorithm. We evaluate our algorithm through integrating it into the existing filtering architecture and implementing this integration scheme on the emulated DDoS scenarios based on real-world Internet topology. Our evaluation results show that compared to the state-of-the-art source-ends filtering scheme Active Internet Traffic Filtering, this integration scheme only uses 20% of its AFRs to achieve more than 70% of its protection effect. Copyright © 2013 John Wiley & Sons, Ltd.

ABSTRACT In recent years, large amounts of graph‐structured data have been outsourced to the commercial public cloud. It is a crucial requirement to enable substructure similarity query for effective data retrieval. However, for protecting data privacy, sensitive data have to be encrypted before outsourcing, which impedes the traditional similarity query schemes from being supported in cloud. Most existing works on encrypted cloud data retrieval pay little attention to this problem. Additionally, considering the huge amounts of encrypted data graphs, the complicated similarity computation and privacy requirements, it is particularly challenging to solve this problem effectively. In this paper, for the first time, we investigate the problem of privacy‐assured substructure similarity query over encrypted graph‐structured data in cloud computing. Our solution explores a secure framework and a series of secure algorithms to efficiently perform the substructure similarity query without privacy breaches. The proposed solution first builds a secure feature‐graph index to represent the feature‐related information about each encrypted data graph based on privacy homomorphism and obscuration methods and then calculates the similarity between the query graph and each data graph by the difference of feature frequency in a privacy‐preserving manner. Thorough analysis is given to investigate effectiveness and privacy guarantees, and the experiments with real dataset further demonstrate the validity and efficiency of the proposed solution. Copyright © 2013 John Wiley & Sons, Ltd.

Virtual network embedding, which means mapping virtual networks requested by users to a shared substrate network maintained by an Internet service provider, is a key function that network virtualization needs to provide. Prior work on virtual network embedding has primarily focused on maximizing the revenue of the Internet service provider and did not consider the energy cost in accommodating such requests. As energy cost is more than half of the operating cost of the substrate networks, while trying to accommodate more virtual network requests, minimizing energy cost is critical for infrastructure providers. In this paper, we make the first effort toward energy-aware virtual network embedding. We first propose an energy cost model and formulate the energy-aware virtual network embedding problem as an integer linear programming problem. We then propose two efficient energy-aware virtual network embedding algorithms: a heuristic-based algorithm and a particle-swarm-optimization-technique-based algorithm. We implemented our algorithms in C++ and performed side-by-side comparison with prior algorithms. The simulation results show that our algorithms significantly reduce the energy cost by up to 50% over the existing algorithm for accommodating the same sequence of virtual network requests.

Co-clustering is a powerful data mining tool for co-occurrence and dyadic data. As data sets become increasingly large, the scalability of co-clustering becomes more and more important. In this paper, we propose two approaches to parallelize co-clustering with sequential updates in a distributed environment. Based on these two approaches, we present a new distributed framework, Co-ClusterD, that supports efficient implementations of co-clustering algorithms with sequential updates. We design and implement Co-ClusterD, and show its efficiency through two co-clustering algorithms: fast nonnegative matrix tri-factorization (FNMTF) and information theoretic co-clustering (ITCC). We evaluate our framework on both a local cluster of machines and the Amazon EC2 cloud. Our evaluation shows that co-clustering algorithms implemented in Co-ClusterD can achieve better results and run faster than their traditional concurrent counterparts.

Energy consumption has become a major concern to the widespread deployment of cloud data centers. The growing importance for parallel applications in the cloud introduces significant challenges in reducing the power consumption drawn by the hosted servers. In this paper, we propose an enhanced energy-efficient scheduling (EES) algorithm to reduce energy consumption while meeting the performance-based service level agreement (SLA). Since slacking non-critical jobs can achieve significant power saving, we exploit the slack room and allocate them in a global manner in our schedule. Using random generated and real-life application workflows, our results demonstrate that EES is able to reduce considerable energy consumption while still meeting SLA.

How to achieve energy efficiency to run a cloud data center is a major challenge in the era of rising electricity cost and environmental protection. Various techniques have been devised to help reduce energy consumption for cloud data centers that consist of a large number of identical servers, including dynamic allocation of active servers, consolidating diverse applications to run on them, and adjusting the CPU speed of an active server. Leveraging these techniques, we use an Online Coloring Bin Packing problem to model the consolidation problem and devise an effective application-aware approximation algorithm to find a near-optimal solution. We show a 1.7 asymptotic approximation ratio. We then apply a Predictive Bayesian Network model to identify daily workload patterns and adjust resource provisioning accordingly. We evaluate our approaches using traces collected from a real data center and demonstrate that (1) our prediction algorithm is effective in estimating future demands, (2) our coordinated approaches can provide significant savings of energy and operational costs close to the near-optimal offline solution, and (3) our approaches incur little reliability costs in term of wear-and-tear of server components.

In light of rapid increase of electricity cost, many business organizations have to find new ways to cut the electricity bill. This paper studies how to reduce the electricity cost in geographical inter-domain virtual network embedding, which embeds virtual networks requested by users to multiple geographically distributed substrate networks run by an infrastructure provider. Previous researches have primarily focused on finding embedding methods to increase revenues by accommodating more virtual network requests, with little attention to reducing the electricity cost. To bridge this gap, we formulate an electricity cost model and design an efficient cost-aware virtual network embedding algorithm by exploiting the location-varying and time-varying diversities of the electricity price and optimizing the energy consumption. Through extensive simulations, we show that our algorithm can significantly reduce the electricity cost by up to 21% over the existing cost-oblivious algorithm, while maintaining nearly the same revenues for the infrastructure provider.

Bulk data transfers account for a large portion of inter-datacenter traffic, such as backups, propagation of bulky updates and migration of data. These bulk data transfers not only consume massive inter-datacenter bandwidth, but also increase the transmission cost of datacenters. To solve this problem, we first employ the max-min fairness to the design of optimal multiple bulk data transfers scheduling algorithm, which leverages the delay tolerance nature of bulk data and reuses dynamic leftover bandwidth to complete multiple bulk data transfers. Then we apply time-expanded technique to transform the problem under a dynamic network into a static network multi-flow problem, and solve it simultaneously from both routing assignment and bandwidth allocation through iterative linear programming approach. Extensive simulations are conducted on a real datacenter topology to demonstrate that our solutions can: 1) improve the network resource utilization; 2) minimize the average bulk data transfer completion time.

Logging-based approaches are suitable for tracing single-packet attacks but incur heavy overhead for packet-digest storage as well as time overhead for both path recording and recovery. Marking-based approaches incur little trace back overhead but are unable to trace single-packet attacks. Recent researches suggest that hybrid approaches are more promising in efficiently tracing single-packet attacks. The major challenge lies in reducing storage and time overhead while maintaining single-packet trace back capability. We presented in this paper a more efficient hybrid approach by designing a novel path fragment encoding scheme using the orthogonality of Walsh matrix and the degree distribution characteristic of router-level topology. Compared to HIT, the most efficient hybrid approach for single-packet trace back to our best knowledge, our approach reduces 2/3 of the overhead in both storage and time for recording packet paths, and the time over-head for recovering packet paths is also reduced by a calculatable amount.

Multicast benefits group communications in saving network traffic and improving application throughput, both of which are important for data center applications. However, the technical trend of data center design poses new challenges for efficient and scalable multicast routing. First, the densely connected networks make traditional receiver-driven multicast routing protocols inefficient in multicast tree formation. Second, it is quite difficult for the low-end switches widely used in data centers to hold the routing entries of massive multicast groups. In this paper, we propose ESM, an efficient and scalable multicast routing scheme for data center networks. ESM addresses the challenges above by exploiting the feature of modern data center networks. Based on the regular topology of data centers, ESM uses a source-to-receiver expansion approach to build efficient multicast trees, excluding many unnecessary intermediate switches used in receiver-driven multicast routing. For scalable multicast routing, ESM combines both in-packet Bloom Filters and in-switch entries to make the tradeoff between the number of multicast groups supported and the additional bandwidth overhead. Simulations show that ESM saves 40%$\sim$50% network traffic and doubles the application throughputs compared to receiver-driven multicast routing, and the combination routing scheme significantly reduces the number of in-switch entries required. We implement ESM on a Linux platform. The experimental results further demonstrate that ESM can well support online tree building for large-scale groups with churns, and the overhead of the combination forwarding engine is light-weighted.

In recent years large graph processing has emerged to be a popular application for companies because of the increasing large Web graph and social networks. The ever growing scale of graphs and recent emergence of cloud computing poses challenges to their efficient and cost-conscious scheduling approach for processing tasks. In this paper, we focus on the use of cloud resources for dispatching large graph processing tasks. We design a novel framework EComer that can be easily integrated into existing cloud infrastructure. The key component of this framework is a cost-conscious scheduling heuristic, called CCSH, which is an extension of Heterogeneous Earliest Finish Time (HEFT). Our algorithm CCSH first constructs a priority list of tasks and then assigns the task with the highest priority value to the cost-efficient virtual machine in a cloud setting. The comparison study, based on randomly generated large graphs and a real-life astronomy application model, demonstrates that our algorithm outperforms HEFT by exhibiting significant monetary cost savings at a reasonable increase in overall execution time.

Free-riding phenomenon is overwhelming in nowadays P2P network which causes researchers to investigate and develop many approaches to combat it. However, almost all the studies neglect the role of relative contribution of peers, namely willingness of contribution (WoC) in our paper. The ignorant to the ratio of peer's actually contribution to its physical capability would undoubtedly lead to unfairly resource allocation and discourage many peers, as well as loose their support in long term. Therefore, in this paper we present a novel and effective approach Cowtra to address such problem. Our algorithm guarantees that the bandwidth of a source node is distributed properly according to the absolute contribution of the competing peers. Then we adjust the amount of competing peers' received bandwidth by utilizing the WoC in the second phase, such that peers with higher WoC obtain more resource while peers with lower WoC otherwise. At last, simulation results demonstrate the superiority of our algorithm in terms of fairness and efficiency.

Next generation wireless network would be a service driven network. As SoftSwitch system could play a very important roll in wireless network, SoftSwitch system also possesses great capabilities in providing services. In this paper, based on the analysis of the architecture of SoftSwitch based wireless network, a variety of service solutions are presented. Moreover, a design scheme of SoftSwitch, which could integrate all service solutions stated in this paper, is proposed.