Graph Neural Networks (GNNs) have recently achieved remarkable performance on the node classification task. While most typical GNN models presume that the graph data is clean, however, graphs could be polluted by various noises that hurt the prediction accuracy. Besides, while GNNs rely on sufficient labeled data to propagate the supervision signal, we should move to a more realistic setting—to learn with a limited amount of labeled data, i.e., label scarcity. In this work, we aim at building a Holistically Robust Graph Neural Network (HRGNN) against four different types of graph noise, including adversarial attacks, edge sparsity, noisy labels, and high heterophily, in the presence of label scarcity. We proposed a novel GNN framework, HRGNN, to fulfill the goal. The main idea of HRGNN is to create synthetic nodes with labels and learn to properly connect them with existing nodes. With synthetic nodes, HRGNN can inject reliable information into existing nodes due to the message-passing mechanism of GNNs that helps purify the polluted representations of nodes and alleviate the negative effect caused by various noises. Furthermore, edge filtering in HRGNN helps remove the noisy edges to prevent the propagation of incorrect information, while pseudo-labeling provides more label information to defend against label scarcity and label noise. Experiments conducted on eight graph datasets exhibit that HRGNN consistently outperforms the state-of-the-art GNN competing models on four types of noisy settings with label scarcity. To the best of our knowledge, HRGNN is the first GNN model that is holistically robust to various types of noise and label scarcity.

This article introduces the Missingness-aware Self-Supervised Graph Neural Network (MissGNN), a novel model for tabular data predictions in scenarios with missing values. Addressing a significant challenge in fields like finance, healthcare, and environmental studies, MissGNN innovatively integrates feature imputation and label prediction within a unified framework. Utilizing a Tabular Bipartite Graph, it distinctively represents data points and features, enabling intricate modeling of their relationships. This approach is pivotal in contexts where missing data can significantly skew model training and predictions. MissGNN employs a Graph Neural Network to generate embeddings, capturing interactions between data points and features for accurate missing value imputation and label prediction. It features a dual-focus mechanism, comprising edge-wise feature imputation and node-wise label prediction. A pre-training phase for feature imputation enhances the model’s predictive ability for both features and labels. Additionally, MissGNN incorporates a multi-view learning strategy through feature subsetting, further enriching its representation learning. Experiments on 14 tabular datasets demonstrate MissGNN’s superiority over existing models in managing missing values across both regression and classification tasks. The results underscore its robustness and practical applicability, establishing it as a versatile tool for tackling tabular data prediction challenges with missing values. MissGNN’s contributions significantly redefine the approach to missing value imputation, aligning feature imputation and label prediction in a cohesive manner and underscoring the potential of Graph Neural Networks in processing tabular data.

Modern and effective recommender systems leverage not only user-item interactions but also private attributes of users to bring promising performance. Protecting private attributes from being inferred by the adversary has become a vital issue in recommender systems. In this work, we formulate the problem of privacy-preserving representation learning for recommendation (PrP-Rec). The design of PrP-Rec is to generate embeddings of users and items so that two inference attacks can be effectively defended. One is item-based attribute inference attack (IAI-Attack), and the other is embedding-based attribute retrieval attack (EAR-Attack). To tackle the PrP-Rec problem, we present a novel framework, privacy-preserving Bayesian personalized ranking (PBPR). The key is to create a learnable gradient obfuscation vector and have it injected into the embedding learning of users and items. The objective of gradient obfuscation is devised to optimize with recommendation and privacy protection. Extensive experiments conducted on three benchmark datasets exhibit that PBPR can outperform competing methods of privacy-preserving recommendation in the top-K recommendation and effectively defending IAI-Attack and EAR-Attack.

Real-world analytics hinges on tabular data, yet prevailing learners face a triple bind: tree ensembles excel on fixed schemas but cannot generalize to new columns, neural nets learn rich features yet overfit small tables, and recent transfer approaches falter when schemas diverge. We tackle these limitations with GTab, a Gradient-Boosting Bipartite Graph Neural Network that marries decision-tree residual refinement with self-supervised graph representation learning. GTab maps each table to an instance-feature bipartite graph, where a GNN, optimised jointly with contrastive, clustering, and reconstruction objectives, captures feature-feature, instance-instance, and cross-type relations. Boosted trees ingest the GNN's gradients, correcting residual errors and injecting the strong inductive bias of split-based models. Building on this backbone, we introduce three variants: E-GTab ensembles multiple overlapping feature sub-graphs for robust classic prediction; I-GTab inductively attaches unseen feature nodes, enabling feature-incremental inference without retraining; and T-GTab pre-trains on a source schema and lightly fine-tunes on a target schema to achieve zero-shot and transfer learning across heterogeneous tables. Across 20 public benchmarks and five clinical trials, GTab consistently ranks first: it outperforms tree, neural, and graph baselines on static tasks, surpasses prior art (and an oracle) when half the test-time columns are unseen, and delivers higher AUC than the leading transformer baseline in both cross-dataset and zero-shot transfer – all with a unified architecture. GTab thus offers a principled, scalable, and adaptable solution to holistic tabular data prediction, bridging the gap between classic ensembles and modern self-supervised representation learning.

Learning from data with missing values is a common challenge in real-world applications. Existing approaches for handling data incompleteness often involve imputation, which can introduce errors that propagate into downstream tasks or impose assumptions that limit the support for heterogeneous feature types. To address these issues, we propose Missing Feature Attention Network ( MFAN ), an end-to-end label prediction model that directly consumes incomplete data without requiring imputation. MFAN flexibly accommodates both continuous and categorical features through learnable embeddings, and leverages a transformer encoder with self-attention to capture the correlation among features as well as the correlation between features and missingness . This attention-based mechanism allows missing features to benefit from relationships learned among observed features, leading to enhanced hidden representations and robust prediction performance. Additionally, we introduce auxiliary self-supervised pre-training tasks that further guide the attention mechanism in modeling missingness. Experimental results on eight regression and seven classification datasets demonstrate MFAN ’s superiority over state-of-the-art end-to-end methods and imputation-based approaches. Comprehensive ablation studies confirm the effectiveness of each MFAN component, underscoring the importance of explicitly modeling correlations among observed and missing features.

Graph Neural Networks (GNNs) are powerful techniques in representation learning for graphs and have been increasingly deployed in a multitude of different applications that involve node- and graph-wise tasks. Most existing studies solve either the node-wise task or the graph-wise task independently while they are inherently correlated. This work proposes a unified model, AdamGNN, to interactively learn node and graph representations in a mutual-optimisation manner. Compared with existing GNN models and graph pooling methods, AdamGNN enhances the node representation with the learned multi-grained semantics and avoids losing node features and graph structure information during pooling. Experiments on 14 real-world graph datasets show that AdamGNN can significantly outperform 17 competing models on both node- and graph-wise tasks. The ablation studies confirm the effectiveness of AdamGNN's components, and the last empirical analysis further reveals the ingenious ability of AdamGNN in capturing long-range interactions. This work was published at IEEE TKDE11Full paper is available at https://ieeexplore.ieee.org/document/9844866/.

Incremental data drifting is a common problem when employing a machine-learning model in industrial applications. The underlying data distribution evolves gradually, e.g., users change their buying preferences on an E-commerce website over time. The problem needs to be addressed to obtain high performance. Right now, studies regarding incremental data drifting suffer from several issues. For one thing, there is a lack of clear-defined incremental drift datasets for examination. Existing efforts use either collected real datasets or synthetic datasets that show two obvious limitations. One is in particular when and of which type of drifts the distribution undergoes is unknown, and the other is that a simple synthesized dataset cannot reflect the complex representation we would normally face in the real world. For another, there lacks a well-defined protocol to evaluate a learner’s knowledge transfer capability on an incremental drift dataset. To provide a holistic discussion on these issues, we create approaches to generate datasets with specific drift types, and define a novel protocol for evaluation. Besides, we investigate recent advances in the transfer learning field, including Domain Adaptation and Lifelong Learning, and examine how they perform in the presence of incremental data drifting. The results unfold the relationships among drift types, knowledge preservation, and learning approaches.

Establishing a robust rumor detection model is vital in safeguarding the veracity of information on social media platforms. However, existing approaches to stopping rumor from spreading rely on abundant and clean training data, which is rarely available in real-world scenarios. In this work, we aim to develop a trustworthy rumor detection model that can handle inadequate and noisy labeled data. Our work addresses robust rumor detection, including classic and early detection, as well as five types of robustness issues: noisy and incomplete propagation, label scarcity and noise, and user disappearance. We propose a novel method, Robustness-Enhanced Rumor Detection (RERD), which mainly leverages the information propagation graphs of source tweets, along with user profiles and retweeting knowledge, for model learning. The novelty of RERD is four-fold. First, we jointly exploit the propagation structures of non-text and text retweets to learn the representation of a source tweet. Second, we simultaneously utilize the top-down and bottom-up information flows with relational propagations for graph representation learning. Third, to have effective early and robust detection, we implement contrastive learning on graphs with early and complete views of information propagation so that small snapshots can foresee their future shapes. Last, we use curriculum pseudo-labeling to mitigate the impact of label scarcity and noisy labels, and to correct representations learned from corrupted data. Experimental results on three benchmark datasets demonstrate that RERD consistently outperforms competitors in classic, early, and robust rumor detection scenarios. To the best of our knowledge, we are the first to simultaneously cope with early and five robust detections of rumors.

The prevalence of disinformation, which includes malformation (e.g., cyberbullying) and misinformation (e.g., fake news) in online platforms has raised significant concerns, prompting the need for robust detection methods to mitigate its detrimental impact. While the field of text classification has witnessed notable advancements in recent years, existing approaches often overlook the evolving nature of disinformation, wherein perpetrators employ perturbations to toxic content to evade detection or censorship. To address this challenge, we present a novel framework, Adversarial Network Towards Improved robustness for Disinformation detection (ANTI-Disinformation), which leverages reinforcement learning techniques as adversarial attacks. Additionally, we propose a defense model to enhance model’s robustness against such attacks. To evaluate the effectiveness of our approach, we conduct extensive experiments on well-known disinformation datasets collected from multiple social media platforms. The results demonstrate our approach can effectively produce degradation in existing models’ performance the most, showcasing the effectiveness of our framework and the vulnerability of existing detection systems. The results also exhibit that the proposed defense methods can consistently outperform existing typical methods in constructing robust detection models.

In today’s data-rich era, large models continuously consume vast troves of personal data, raising pertinent questions about user consent and its implications in training machine learning frameworks. With mounting calls for enhanced user privacy, the “right to be forgotten” is gaining traction in contemporary research. Parallelly, the ubiquity of graph neural networks underscores its ever-growing imprint on artificial intelligence communities, resonating in almost every facet of various applications. This study delves into enhancing the effectiveness of graph unlearning through the incorporation of graph contrastive learning. To adeptly erase edge information without compromising the performance of the subsequent link prediction task. We present a novel graph unlearning framework, Graph Contrastive Unlearning (GCU). Infusing the principles of contrastive learning into conventional graph unlearning paradigms, the GCU stands out, ensuring the absolute erasure of deleted edge data. The genius of graph contrastive unlearning lies in its dual capability: facilitating the model in discerning the deleted edges from their original counterparts while seamlessly aligning the neighbors of these edges with the original graph’s node features. Crafted meticulously, the GCU extirpates the influence of the removed elements from model parameters and neighboring representations. Yet, it ensures the sanctity and retention of the residual model knowledge post-deletion. Empirical tests underscore the GCU’s promising edge unlearning ability, revealing marked improvements in link prediction across diverse graph datasets. This not only fortifies user privacy but also streamlines the unlearning process, eliminating the cumbersome need for full model retraining even in scenarios of mass edge deletions.

Customs officials across the world encounter huge volumes of transactions. Associated with customs transactions is customs fraud-the intentional manipulation of goods declarations to avoid taxes and duties. Due to limited manpower, the customs offices can only manually inspect a small number of declarations, necessitating the automation of customs fraud detection by machine learning techniques. The limited availability of manually inspected ground truth data makes it essential for the ML approach to generalize well on unseen data. However, current customs fraud detection models are not well suited or designed for this setting. In this work, we propose GraphFC (Graph Neural networks for Customs Fraud), a model-agnostic, domain-specific, graph neural network based customs fraud detection model that is designed to work in a real-world setting with limited ground truth data. Extensive experimentation using real customs data from two countries demonstrates that GraphFC generalizes well over unseen data and outperforms various baselines and other models by a large margin.

Deep learning-based approaches to Tabular Data Learning (TDL) have shown promising performance compared to their conventional counterparts. However, these methods often fail to account for the latent correlation among data instances and feature values. Recently, graph neural networks (GNNs) have gained attention across various application domains, including TDL, for their ability to model relations and interactions between different data entities. By creating appropriate graph structures from the input tabular data and employing GNNs for learning, the performance of TDL can be improved significantly. In this tutorial, we systematically introduce the methodologies of designing and applying GNNs to TDL. Our discussion covers the foundations and overview of GNN-based TDL methods, with a focus on formulating TDL as different graph structures. We also provide a comprehensive taxonomy of constructing graph structures and representation learning in GNN-based TDL methods. We describe the TDL model training framework, which includes different auxiliary tasks and supports open-world learning. Additionally, we discuss how to apply GNNs to various TDL application scenarios and tasks. Finally, we outline the limitations of current research and future directions for this field.

Abstract Graph Neural Networks (GNNs) have become a prominent approach to machine learning with graphs and have been increasingly applied in a multitude of domains. Nevertheless, since most existing GNN models are based on flat message-passing mechanisms, two limitations need to be tackled: (i) they are costly in encoding long-range information spanning the graph structure; (ii) they are failing to encode features in the high-order neighbourhood in the graphs as they only perform information aggregation across the observed edges in the original graph. To deal with these two issues, we propose a novel Hierarchical Message-passing Graph Neural Networks framework. The key idea is generating a hierarchical structure that re-organises all nodes in a flat graph into multi-level super graphs, along with innovative intra- and inter-level propagation manners. The derived hierarchy creates shortcuts connecting far-away nodes so that informative long-range interactions can be efficiently accessed via message passing and incorporates meso- and macro-level semantics into the learned node representations. We present the first model to implement this framework, termed Hierarchical Community-aware Graph Neural Network (HC-GNN), with the assistance of a hierarchical community detection algorithm. The theoretical analysis illustrates HC-GNN’s remarkable capacity in capturing long-range information without introducing heavy additional computation complexity. Empirical experiments conducted on 9 datasets under transductive, inductive, and few-shot settings exhibit that HC-GNN can outperform state-of-the-art GNN models in network analysis tasks, including node classification, link prediction, and community detection. Moreover, the model analysis further demonstrates HC-GNN’s robustness facing graph sparsity and the flexibility in incorporating different GNN encoders.

Neural Architecture Search (NAS) has shown promising capability in learning text representation. However, existing text-based NAS neither performs a learnable fusion of neural operations to optimize the architecture nor encodes the latent hierarchical categorization behind text input. This article presents a novel NAS method, Discretized Differentiable Neural Architecture Search (DDNAS), for text representation learning and classification. With the continuous relaxation of architecture representation, DDNAS can use gradient descent to optimize the search. We also propose a novel discretization layer via mutual information maximization, which is imposed on every search node to model the latent hierarchical categorization in text representation. Extensive experiments conducted on eight diverse real datasets exhibit that DDNAS can consistently outperform the state-of-the-art NAS methods. While DDNAS relies on only three basic operations, i.e., convolution, pooling, and none, to be the candidates of NAS building blocks, its promising performance is noticeable and extensible to obtain further improvement by adding more different operations.

Deep learning shows superiority in learning feature representations that offer promising performance in various application domains. Recent advances have shown that privacy attributes of users and patients (e.g., identity, gender, and race) can be accurately inferred from image data. To avoid the risk of privacy leaking, data owners can resort to releasing the embeddings rather than the original images. In this article, we aim at learning to generate privacy-preserving embeddings from image data. The obtained embeddings are required to maintain the data utility (e.g., keeping the performance of the main task, such as disease prediction) and to simultaneously prevent the private attributes of data instances from being accurately inferred. We also want the hard embeddings to be successfully used to reconstruct the original images. We propose a hybrid method based on multi-task learning to reach the goal. The key idea is twofold. One is to learn the feature encoder that can benefit the main task and fool the sensitive task at the same time via iterative training and feature disentanglement. The other is to incorporate the learning of adversarial examples to mislead the sensitive attribute classification’s performance. Experiments conducted on Multi-Attribute Facial Landmark (MAFL) and NIH Chest X-ray datasets exhibit the effectiveness of our hybrid method. A set of advanced studies also shows the usefulness of each model component, the difficulty in data reconstruction, and the performance impact of task correlation.

Attributed network embedding (ANE) is to learn low-dimensional vectors so that not only the network structure but also node attributes can be preserved in the embedding space. Existing ANE models do not consider the specific combination between graph structure and attributes. While each node has its structural characteristics, such as highly-interconnected neighbors along with their certain patterns of attribute distribution, each node's neighborhood should be not only depicted by multi-hop nodes, but consider certain clusters or social circles. To model such information, in this paper, we propose a novel ANE model,Context Co-occurrence-aware Attributed Network Embedding(CoANE). The basic idea of CoANE is to model the context attributes that each node's involved diverse patterns, and apply the convolutional mechanism to encode positional information by treating each attribute as a channel. The learning of context co-occurrence can capture the latent social circles of each node. To better encode structural and semantic knowledge of nodes, we devise a three-way objective function, consisting of positive graph likelihood, contextual negative sampling, and attribute reconstruction. We conduct experiments on five real datasets in the tasks of link prediction, node label classification, and node clustering. The results exhibit that CoANE can significantly outperform state-of-the-art ANE models.

Recent advances in protecting node privacy on graph data and attacking graph neural networks (GNNs) gain much attention. The eye does not bring these two essential tasks together yet. Imagine an adversary can utilize the powerful GNNs to infer users’ private labels in a social network. How can we adversarially defend against such privacy attacks while maintaining the utility of perturbed graphs? In this work, we propose a novel research task, adversarial defenses against GNN-based privacy attacks, and present a graph perturbation-based approach, NetFense, to achieve the goal. NetFense can simultaneously keep graph data unnoticeability (i.e., having limited changes on the graph structure), maintain the prediction confidence of targeted label classification (i.e., preserving data utility), and reduce the prediction confidence of private label classification (i.e., protecting the privacy of nodes). Experiments conducted on single- and multiple-target perturbations using three real graph data exhibit that the perturbed graphs by NetFense can effectively maintain data utility (i.e., model unnoticeability) on targeted label classification and significantly decrease the prediction confidence of private label classification (i.e., privacy protection). Extensive studies also bring several insights, such as the flexibility of NetFense, preserving local neighborhoods in data unnoticeability, and better privacy protection for high-degree nodes.

Financial technology (FinTech) has drawn much attention among investors and companies. While conventional stock analysis in FinTech targets at predicting stock prices, less effort is made for profitable stock recommendation. Besides, in existing approaches on modeling time series of stock prices, the relationships among stocks and sectors (i.e., categories of stocks) are either neglected or pre-defined. Ignoring stock relationships will miss the information shared between stocks while using pre-defined relationships cannot depict the latent interactions or influence of stock prices between stocks. In this work, we aim at recommending the top-K profitable stocks in terms of return ratio using time series of stock prices and sector information. We propose a novel deep learning-based model, Financial Graph Attention Networks (FinGAT), to tackle the task under the setting that no pre-defined relationships between stocks are given. The idea of FinGAT is three-fold. First, we devise a hierarchical learning component to learn short-term and long-term sequential patterns from stock time series. Second, a fully-connected graph between stocks and a fully-connected graph between sectors are constructed, along with graph attention networks, to learn the latent interactions among stocks and sectors. Third, a multi-task objective is devised to jointly recommend the profitable stocks and predict the stock movement. Experiments conducted on Taiwan Stock, S&P 500, and NASDAQ datasets exhibit remarkable recommendation performance of our FinGAT, comparing to state-of-the-art methods.

Graph Neural Networks (GNNs) are powerful techniques in representation learning for graphs and have been increasingly deployed in a multitude of different applications that involve node- and graph-wise tasks. Most existing studies solve either the node-wise task or the graph-wise task independently while they are inherently correlated. This work proposes a unified model, AdamGNN, to interactively learn node and graph representations in a mutual-optimisation manner. Compared with existing GNN models and graph pooling methods, AdamGNN enhances the node representation with the learned multi-grained semantics and avoids losing node features and graph structure information during pooling. Specifically, a differentiable pooling operator is proposed to adaptively generate a multi-grained structure that involves meso- and macro-level semantic information in the graph. We also devise the unpooling operator and theflybackaggregator in AdamGNN to better leverage the multi-grained semantics to enhance node representations. The updated node representations can further adjust the graph representation in the next iteration. Experiments on 14 real-world graph datasets show that AdamGNN can significantly outperform 17 competing models on both node- and graph-wise tasks. The ablation studies confirm the effectiveness of AdamGNN's components, and the last empirical analysis further reveals the ingenious ability of AdamGNN in capturing long-range interactions.

While social media is prevalent in people’s daily life, privacy control of user-generated posts is becoming increasingly important. In this paper, we propose to enable automatic privacy control for social media posts through two tasks, predicting privacy settings and predicting privacy categories. The former is to recommend the proper settings of privacy levels, including family, close, casual, and outside, for a post. The latter is to predict the categories of privacy concerns for a post. We propose a multi-task learning-based approach, along with learning feature representation of each post, for such two tasks. Experiments conducted on a real dataset with tweet posts exhibit promising performance of our model, and thus encourage further investigation of privacy-related tasks for privacy control on social media. We also provide a series of extensive analysis with insights that reveal the hidden correlation between privacy settings/categories and post texts.

As the urban population rises, so does the pressure on the city’s transportation system. Most of the existing methods for passenger destination selection focus on processing the historical behaviors and travel trajectories of passengers. However, the existing methods face the generalization issue, the trained model cannot be applied to predict destinations in new metropolitan areas as the destination information is totally unseen and different from the training sets. To deal with the issue faced in IEEE BigData Cup 2022 – Trip Destination Prediction, in this work, we present a hybrid method. The main idea of our method is four-fold. The first is to implement the gravity model to capture human mobility between zones. The second contains two novel features to depict zones, including human traffic flow and feature class ratio. The third is to initialize the destinations in the new metropolitan area using the origin zones of multi-trip individuals. The last is to perform the nearest-neighbor search on both individuals and trips. The final destination prediction is produced by combining the gravity model and the nearest-neighbor search. Performance comparison reported by the competition leaderboard exhibits the superiority of our hybrid method, which also brings us to the fifth place in the competition.

In this paper, we propose the Rule-based Visiting Circulation (RVC) model in tackling the challenge in the IEEE Big Data Cup 2022: Trip Destination Prediction. Given trips containing travel information, personal attributes, origin zones, and their features in the training metropolitan areas, the task is to predict the destination of every trip in a targeted metropolitan area whose destinations are not given at all at the training stage. We highlight the challenges in this destination prediction task – having no knowledge of the destinations in the targeted metropolitan area. We provide insights from the datasets, in which revisiting behaviors and the relationships between origins and destinations play a crucial role in individuals’ trips. Hence, we design a simple but comprehensive method, rule-based visiting circulation, which directly utilizes the origin information and individuals’ trip behaviors to determine the destinations in the targeted metropolitan area, i.e., requiring no learning from the four training areas. Experimental results on both offline evaluation and leaderboard submission consistently exhibit the proposed RVC can significantly outperform supervised learning methods and other heuristics. The RVC method eventually brings us to second place in the competition leaderboard.

Attributed network embedding (ANE) is to learn low-dimensional vectors so that not only the network structure but also node attributes can be preserved in embeddings. Existing ANE models do not consider the specific combination between graph structure and attributes. While each node has its structural characteristics, such as highly-interconnected neighbors along with their certain patterns of attribute distribution, each node's neighborhood should be not only depicted by multi-hop nodes, but consider certain social circles. To model such information, in this paper, we propose a novel ANE model, Context Co-occurrence-aware Attributed Network Embedding (CoANE). The basic idea of CoANE is to model the context attributes for each node, and apply the convolutional mechanism to encode latent social circles. To better preserve network knowledge, we devise objective functions including positive graph likelihood, contextual negative sampling, and attribute reconstruction. We conduct experiments on five real datasets for downstream tasks, including node classification, link prediction, and community detection. The results exhibit that CoANE can significantly outperform state-of-the-art ANE models. This work was accepted to IEEE TKDE11Full paper is available at https://ieeexplore.ieee.org/document/9431700.

Abstract Recently, increasing attention has been paid to heterogeneous graph representation learning (HGRL), which aims to embed rich structural and semantic information in heterogeneous information networks (HINs) into low-dimensional node representations. To date, most HGRL models rely on hand-crafted meta-paths. However, the dependency on manually-defined meta-paths requires domain knowledge, which is difficult to obtain for complex HINs. More importantly, the pre-defined or generated meta-paths of all existing HGRL methods attached to each node type or node pair cannot be personalised to each individual node. To fully unleash the power of HGRL, we present a novel framework, Personalised Meta-path based Heterogeneous Graph Neural Networks (PM-HGNN), to jointly generate meta-paths that are personalised for each individual node in a HIN and learn node representations for the target downstream task like node classification. Precisely, PM-HGNN treats the meta-path generation as a Markov Decision Process and utilises a policy network to adaptively generate a meta-path for each individual node and simultaneously learn effective node representations. The policy network is trained with deep reinforcement learning by exploiting the performance improvement on a downstream task. We further propose an extension, PM-HGNN++, to better encode relational structure and accelerate the training during the meta-path generation. Experimental results reveal that both PM-HGNN and PM-HGNN++ can significantly and consistently outperform 16 competing baselines and state-of-the-art methods in various settings of node classification. Qualitative analysis also shows that PM-HGNN++ can identify meaningful meta-paths overlooked by human knowledge.

Sequential recommendation (SR) learns from the temporal dynamics of user-item interactions to predict the next ones. Fairness-aware recommendation mitigates a variety of algorithmic biases in the learning of user preferences. This article aims at bringing a marriage between SR and algorithmic fairness. We propose a novel fairness-aware sequential recommendation task, in which a new metric, interaction fairness , is defined to estimate how recommended items are fairly interacted by users with different protected attribute groups. We propose a multi-task learning-based deep end-to-end model, FairSR, which consists of two parts. One is to learn and distill personalized sequential features from the given user and her item sequence for SR. The other is fairness-aware preference graph embedding (FPGE). The aim of FPGE is two-fold: incorporating the knowledge of users’ and items’ attributes and their correlation into entity representations, and alleviating the unfair distributions of user attributes on items. Extensive experiments conducted on three datasets show FairSR can outperform state-of-the-art SR models in recommendation performance. In addition, the recommended items by FairSR also exhibit promising interaction fairness.

Top-N sequential recommendation is to predict the next few items based on user's sequential interactions with past items. This paper aims at boosting the performance of top-N sequential recommendation based on a state-of-the-art model, Caser. We point out three insufficiencies of Caser - do not model variant-sized sequential patterns, treating the impact of each past time step equally, and cannot learn cumulative features. Then we propose a novel Convolutional Attentional Recurrent Embedding (CARE) learning model. Experiments conducted on a large-scale user-location check-in dataset exhibit promising performance, comparing to Caser.

While Wikipedia has been utilized for fact-checking and claim verification to debunk misinformation and disinformation, it is essential to either improve article quality and rule out noisy articles. Self-contradiction is one of the low-quality article types in Wikipedia. In this work, we propose a task of detecting self-contradiction articles in Wikipedia. Based on the "self-contradictory" template, we create a novel dataset for the self-contradiction detection task. Conventional contradiction detection focuses on comparing pairs of sentences or claims, but self-contradiction detection needs to further reason the semantics of an article and simultaneously learn the contradiction-aware comparison from all pairs of sentences. Therefore, we present the first model, Pairwise Contradiction Neural Network (PCNN), to not only effectively identify self-contradiction articles, but also highlight the most contradiction pairs of contradiction sentences. The main idea of PCNN is two-fold. First, to mitigate the effect of data scarcity on self-contradiction articles, we pre-train the module of pairwise contradiction learning using SNLI and MNLI benchmarks. Second, we select top-K sentence pairs with the highest contradiction probability values and model their correlation to determine whether the corresponding article belongs to self-contradiction. Experiments conducted on the proposed WikiContradiction dataset exhibit that PCNN can generate promising performance and comprehensively highlight the sentence pairs the contradiction locates.

Competitive Influence Maximization (CIM) aims to maximize the influence of a party given the competition from other parties in the same social network, like companies find key users to promote their competitive products on the social network to achieve maximum profit. Recently, learning-based solutions are introduced to tackle the competitive influence maximization problem. However, such studies focus on the static nature of social networks. This paper proposes a deep reinforcement learning-based framework employing network embedding, termed as DRL-EMB, to tackle the CIM problem on evolving social networks. The DRL-EMB key objective is to find the best strategy to maximize the party's reward, considering budget and competition with information propagation and network evolving being run in parallel. We validate our proposed framework with the DRL-based model using hand-crafted state features (DRL-HCF) and heuristic-based methods. Experimental results show that our proposed framework, DRL-EMB, achieves better results than heuristic-based and DRL-HCF models while significantly outperforming the DRL-HCF model in terms of time efficiency.

Sequential recommendation (SR) is to accurately recommend a list of items for a user based on her current accessed ones. While new-coming users continuously arrive in the real world, one crucial task is to have inductive SR that can produce embeddings of users and items without re-training. Given user-item interactions can be extremely sparse, another critical task is to have transferable SR that can transfer the knowledge derived from one domain with rich data to another domain. In this work, we aim to present the holistic SR that simultaneously accommodates conventional, inductive, and transferable settings. We propose a novel deep learning-based model, Relational Temporal Attentive Graph Neural Networks (RetaGNN), for holistic SR. The main idea of RetaGNN is three-fold. First, to have inductive and transferable capabilities, we train a relational attentive GNN on the local subgraph extracted from a user-item pair, in which the learnable weight matrices are on various relations among users, items, and attributes, rather than nodes or edges. Second, long-term and short-term temporal patterns of user preferences are encoded by a proposed sequential self-attention mechanism. Third, a relation-aware regularization term is devised for better training of RetaGNN. Experiments conducted on MovieLens, Instagram, and Book-Crossing datasets exhibit that RetaGNN can outperform state-of-the-art methods under conventional, inductive, and transferable settings. The derived attention weights also bring model explainability.

Demographic information is important for various commercial and academic proposes, but in reality, few of these data are accessible for analysis and research. To solve this problem, several studies predict demographic attributes from users’ behavioral data. However, previous works suffer from different kinds of disadvantages. Handling data sparseness and defining useful features remain especially challenge tasks. In this article, we propose a novel Deep Energy Factorization Model to address these two drawbacks. The model is a designed network that performs multi-label classification and feature representation. Experiments are conducted on four datasets with four evaluation metrics. The empirical results show that our Deep Energy Factorization Model significantly outperforms state-of-the-art models.

In this work, we propose a novel recommendation problem, actor recommendation (ActRec), based on unstructured text data for the movie industry. Given the text description of a role, we generate a ranking list of actors such that the most proper actors for the role-playing can be at top positions. We propose a word embedding-based approach to solve the ActRec problem. In addition, we compile a multi-source data from Wikipedia, Google Search, and PTT online forum. Experimental results show the promising performance of our method, which encourages future effort on ActRec.

Self-supervised representation learning aims to generate effective representations for data instances without the need for manual labels, also known as unsupervised embedding learning, which has been a critical challenge in many existing semi-supervised and supervised learning tasks. This paper proposes a new self-supervised learning approach, called Super-AND, which extends the memory-based pretraining method AND model [13]. Super-AND has its unique set of losses that combines data augmentation in neighborhood discovery for more accurate anchor selection in embedding learning and further presents an adversarial training manner to learn more confident embeddings under the unsupervised setting. Experimental results exhibit that Super-AND outperforms all existing state-of-the-art self-supervised representation learning approaches and achieves an accuracy of 89.2% on the image classification task for CIFAR-10.

Forecasting spatio-temporal correlated time series of sensor values is crucial in urban applications, such as air pollution alert, biking resource management, and intelligent transportation systems. While recent advances exploit graph neural networks (GNN) to better learn spatial and temporal dependencies between sensors, they cannot model time-evolving spatio-temporal correlation (STC) between sensors, and require pre-defined graphs, which are neither always available nor totally reliable, and target at only a specific type of sensor data at one time. Moreover, since the form of time-series fluctuation is varied across sensors, a model needs to learn fluctuation modulation. To tackle these issues, in this work, we propose a novel GNN-based model, Attention-adjusted Graph Spatio-Temporal Network (AGSTN). In AGSTN, multi-graph convolution with sequential learning is developed to learn time-evolving STC. Fluctuation modulation is realized by a proposed attention adjustment mechanism. Experiments on three sensor data, air quality, bike demand, and traffic flow, exhibit that AGSTN outperforms the state-of-the-art methods.

Intentional manipulation of invoices that lead to undervaluation of trade goods is the most common type of customs fraud to avoid ad valorem duties and taxes. To secure government revenue without interrupting legitimate trade flows, customs administrations around the world strive to develop ways to detect illicit trades. This paper proposes DATE, a model of Dual-task Attentive Tree-aware Embedding, to classify and rank illegal trade flows that contribute the most to the overall customs revenue when caught. The strength of DATE comes from combining a tree-based model for interpretability and transaction-level embeddings with dual attention mechanisms. To accurately identify illicit transactions and predict tax revenue, DATE learns simultaneously from illicitness and surtax of each transaction. With a five-year amount of customs import data with a test illicit ratio of 2.24%, DATE shows a remarkable precision of 92.7% on illegal cases and a recall of 49.3% on revenue after inspecting only 1% of all trade flows. We also discuss issues on deploying DATE in Nigeria Customs Service, in collaboration with the World Customs Organization.

Recommending individuals through keywords is an essential and common search task in online social platforms such as Facebook and LinkedIn. However, it is often that one has only the impression about the desired targets, depicted by labels of social contexts (e.g. gender, interests, skills, visited locations, employment, etc). Assume each user is associated a set of labels, we propose a novel task, Search by Social Contexts (SSC), in online social networks. SSC is a kind of query-based people recommendation, recommending the desired target based on a set of user-specified query labels. We develop the method Social Query Embedding Learning (SQEL) to deal with SSC. SQEL aims to learn the feature representation (i.e., embedding vector) of the query, along with user feature vectors derived from graph embedding, and use the learned query vectors to find the targets via similarity. Experiments conducted on Facebook and Twitter datasets exhibit satisfying accuracy and encourage more advanced efforts on search by social contexts.

Heterogeneous network is a useful data representation in depicting complex interactions among multi-typed entities and relations. In this work, by representing criminal and terrorism activities as a heterogeneous network, we propose a novel unsupervised method, Outlier Spotting with behavior-aware Network Embedding (OSNE), to identify terrorists among potential criminals. The basic idea of OSNE is to exploit high-order relation paths for translation-based embedding learning, and distinguish same-type entities based on behavior penalty and type-aware negative sampling. We evaluate the effectiveness of OSNE using six criminal network datasets provided by DARPA, and make comparison with strong competitors. The results exhibit the promising performance of OSNE.

Precision psychiatry is a new research field that uses advanced data mining over a wide range of neural, behavioral, psychological, and physiological data sources for classification of mental health conditions. This study presents a computational framework for predicting sleep efficiency of insomnia sufferers. A smart band experiment is conducted to collect heterogeneous data, including sleep records, daily activities, and demographics, whose missing values are imputed via Improved Generative Adversarial Imputation Networks (Imp-GAIN). Equipped with the imputed data, we predict sleep efficiency of individual users with a proposed interpretable LSTM-Attention (LA Block) neural network model. We also propose a model, Pairwise Learning-based Ranking Generation (PLRG), to rank users with high insomnia potential in the next day. We discuss implications of our findings from the perspective of a psychiatric practitioner. Our computational framework can be used for other applications that analyze and handle noisy and incomplete time-series human activity data in the domain of precision psychiatry.

Financial technology (FinTech) draws much attention in these years, with the advances of machine learning and deep learning. In this work, given historical time series of stock prices of companies, we aim at forecasting upcoming anomalous financial items, i.e., abrupt soaring or diving stocks, in financial time series, and recommending the corresponding stocks to support financial operations. We propose a novel joint convolutional and recurrent neural network model, Financial Event Neural Network (FineNet), to forecast and recommend anomalous stocks. Experiments conducted on the time series of stock prices of 300 well-known companies exhibit the promising performance of FineNet in terms of precision and recall. We build FineNet as a Web platform for live demonstration.

Network embedding aims at learning an effective vector transformation for entities in a network. We observe that there are two diverse branches of network embedding: for homogeneous graphs and for multi-relational graphs. This paper then proposes MARINE, a unified embedding framework for both homogeneous and multi-relational networks to preserve both the proximity and relation information. We also extend the framework to incorporate existing features of nodes in a graph, which can further be exploited for the ensemble of embedding. Our solution possesses complexity linear to the number of edges, which is suitable for large-scale network applications. Experiments conducted on several real-world network datasets, along with applications in link prediction and multi-label classification, exhibit the superiority of our proposed MARINE.

As mobile devices are becoming ubiquitous nowadays, the geographical activities and interactions of human beings can be easily recorded and accessed. Each mobile individual can belong to an online social network. Unfortunately, the underlying online social relationships are hidden and only available to service providers. Acquiring the social network of mobile users would enrich lots of mobile applications, such as friend recommendation and energy-saving mobile database management. In this work, we propose to infer online social ties using purely offline geographical activities of users, such as check-in records and spatial meeting events. To tackle the problem, we devise a novel inference framework, O2O-I nf , which consists of two components, Feature Modeling and Link Inference . Feature modeling is to characterize both direct and indirect geographical interactions between nodes from co-location and graph features. Link inference aims to infer the social ties based on a small set of observed social links, and the idea is that pairs of nodes sharing similar geographical behaviors have the same tendency of linkage (i.e., either being friends or non-friends). Experiments conducted on a G owalla location-based social network and a M eetup event-based social network exhibit a satisfying performance in comparison to state-of-the-art prediction methods under the settings of offline-to-online network inference and geo-link prediction.

Online streaming services are prevalent. Major service providers, such as Netflix (for movies) and Spotify (for music), usually have a large customer base. More often than not, users may share an account. This has attracted increasing attention recently, as account sharing not only compromises the service provider's financial interests but also impairs the performance of recommendation systems and consequently the quality of service provided to the users. To address this issue, this paper focuses on the problem of user identification in shared accounts. Our goal is three-fold: (1) Given an account, along with its historical session logs, we identify a set of users who share such account; (2) Given a new session issued by an account, we find the corresponding user among the identified users of such account; (3) We aim to boost the performance of item recommendation by user identification. While the mapping between users and accounts is unknown, we propose an unsupervised learning-based framework, Session-based Heterogeneous graph Embedding for User Identification (SHE-UI), to differentiate and model the preferences of users in an account, and to group sessions by these users. In SHE-UI, a heterogeneous graph is constructed to represent items such as songs and their available metadata such as artists, genres, and albums. An item-based session embedding technique is proposed using a normalized random walk in the heterogeneous graph. Our experiments conducted on two large-scale music streaming datasets, Last.fm and KKBOX, show that SHE-UI not only accurately identifies users, but also significantly improves the performance of item recommendation over the state-of-the-art methods.

Hashtag has emerged as a widely used concept of popular culture and campaigns, but its implications on people»s privacy have not been investigated so far. In this paper, we present the first systematic analysis of privacy issues induced by hashtags. We concentrate in particular on location, which is recognized as one of the key privacy concerns in the Internet era. By relying on a random forest model, we show that we can infer a user»s precise location from hashtags with accuracy of 70% to 76%, depending on the city. To remedy this situation, we introduce a system called Tagvisor that systematically suggests alternative hashtags if the user-selected ones constitute a threat to location privacy. Tagvisor realizes this by means of three conceptually different obfuscation techniques and a semantics-based metric for measuring the consequent utility loss. Our findings show that obfuscating as little as two hashtags already provides a near-optimal trade-off between privacy and utility in our dataset. This in particular renders Tagvisor highly time-efficient, and thus, practical in real-world settings.

Recommender systems are common in e-commerce platforms in recent years. Recommender systems are able to help users find preferential items among a large amount of products so that users’ time is saved and sellers’ profits are increased. Cross-domain recommender systems aim to recommend items based on users’ different tastes across domains. While recommender systems usually suffer from the user cold-start problem that leads to unsatisfying recommendation performance, cross-domain recommendation can remedy such a problem. This article proposes a novel cross-domain recommendation model based on regression analysis, partial least squares regression (PLSR). The proposed recommendation models, PLSR-CrossRec and PLSR-Latent, are able to purely use source-domain ratings to predict the ratings for cold-start users who never rated items in the target domains. Experiments conducted on the Epinions dataset with ten various domains’ rating records demonstrate that PLSR-Latent can outperform several matrix factorization-based competing methods under a variety of cross-domain settings. The time efficiency of PLSR-Latent is also satisfactory.

Social networking websites allow users to create and share a variety of items. Big information cascades of post resharing can be generated because users of these sites reshare each other's posts with their friends and followers. In this work, we aim at predicting the final number of reshares for any given post. We build on the theory of self-exciting point processes to develop a statistical model, PSEISMIC, which leads to accurate predictions of popularity. Moreover, we perform cluster analysis to group all tweets so that the coefficient of memory kernel in PSEISMIC can be estimated for every cluster, rather than using the same memory kernel. Experiments conducted on a large-scale retweet dataset show that the proposed PSEISMIC model outperforms the state-of-the-art approach, SEISMIC in predicting the popularity of a given post.

Nowadays, geosensor data, such as air quality and traffic flow, have become more and more essential in people's daily life. However, installing geosensors or hiring volunteers at every location and every time is so expensive. Some organizations may have only few facilities or limited budget to sense these data. Moreover, people usually tend to know the forecast instead of ongoing observations, but the number of sensors (or volunteers) will be a hurdle to make precise prediction. In this paper, we propose a novel concept to forecast geosensor data with participatory sensing. Given a limited number of sensors or volunteers, participatory sensing assumes each of them can observe and collect data at different locations and at different time. By aggregating these sparse data observations in the past time, we propose a neural network based approach to forecast the future geosensor data in any location of an urban area. The extensive experiments have been conducted with large-scale datasets of the air quality in three cities and the traffic of bike sharing systems in two cities. Experimental results show that our predictive model can precisely forecast the air quality and the bike rentle traffic as geosensor data.

In recent years, online social networks are among the most popular websites with high PV (Page View) all over the world, as they have renewed the way for information discovery and distribution. Millions of users have registered on these websites and hence generate formidable amount of user-generated contents every day. The social networks become "giants", likely eligible to carry on any research tasks. However, we have pointed out that these giants still suffer from their "Achilles Heel", i.e., extreme sparsity. Compared with the extremely large data over the whole collection, individual posting documents such as microblogs seem to be too sparse to make a difference under various research scenarios, while actually these postings are different. In this paper we propose to tackle the Achilles Heel of social networks by smoothing the language model via influence propagation. To further our previously proposed work to tackle the sparsity issue, we extend the socialized language model smoothing with bi-directional influence learned from propagation. Intuitively, it is insufficient not to distinguish the influence propagated between information source and target without directions. Hence, we formulate a bi-directional socialized factor graph model, which utilizes both the textual correlations between document pairs and the socialized augmentation networks behind the documents, such as user relationships and social interactions. These factors are modeled as attributes and dependencies among documents and their corresponding users, and then are distinguished on the direction level. We propose an effective learning algorithm to learn the proposed factor graph model with directions. Finally we propagate term counts to smooth documents based on the estimated influence. We run experiments on two instinctive datasets of Twitter and Weibo. The results validate the effectiveness of the proposed model. By incorporating direction information into the socialized language model smoothing, our approach obtains improvement over several alternative methods on both intrinsic and extrinsic evaluations measured in terms of perplexity, nDCG and MAP measurements.

Online social connections allow users to share and spread information with others. Different users play various roles on information diffusion: some are influential within a community and some make information widely spread across communities. This paper aims to unveil the hidden relationships between nodes and information diffusion in the context of communities from the big Twitter diffusion data with a million-scale social network, as a complement to existing link-based diffusion analysis (e.g. the strength of weak ties). We identify six types of well-known community-aware roles of nodes, and examine their diffusion capability on propagating information within/across communities, using information flows via retweet and mention in Twitter. We find nodes acting as community bridges are exposed to more information and more dominative on spread information within/across communities. Community-aware roles are also validated via supervised learning to be effective for detecting the most diffusive information propagators.

This paper proposes to study a novel problem, discovering a Smallest Unique Subgraph (SUS) for any node of interest specified by user in a heterogeneous social network. The rationale of the SUS problem lies in how a person is different from any others in a social network, and how to represent the identity of a person using her surrounding relational structure in a social network. To deal with the proposed SUS problem, we develop an Ego-Graph Heuristic (EGH) method to efficiently solve the SUS problem in an approximated manner. EGH intelligently examine whether one graph is not isomorphic to the other, instead of using the conventional subgraph isomorphism test. We also prove SUS is a NP-complete problem through doing a reduction from Minimum Vertex Cover (MVC) in a homogeneous tree structure. Experimental results conducted on a real-world movie heterogeneous social network data show both the promising efficiency and compactness of our method.

This paper aims to investigate how the geographical footprints of users correlate to their social ties. While conventional wisdom told us that the more frequently two users co-locate in geography, the higher probability they are friends, we find that in real geo-social data, Gowalla and Meetup, almost all of the user pairs with friendships had never met geographically. In this sense, can we discover social ties among users purely using their geographical footprints even if they never met? To study this question, we develop a two-stage feature engineering framework. The first stage is to characterize the direct linkages between users through their spatial co-locations while the second is to capture the indirect linkages between them via a co-location graph. Experiments conducted on Gowalla check-in data and Meetup meeting events exhibit not only the superiority of our feature model, but also validate the predictability (with 70% accuracy) of detecting social ties solely from user footprints.

Searching for a particular person by specifying her name is one of the essential functions in online social networking services such as Facebook. So many times, however, one would like to find a person but what she knows is few social labels about the target, such as interests, skills, hometown, school, employment, etc. Assume each user is associated a set of social labels, we propose a novel search in online social network, Person-of-Interest (POI) Search, which aims to find a list of desired targets based on a set of user-specified query labels that depict the targets. We develop a greedy heuristic graph search algorithm, which finds the target who not only covers the query labels, but also either possesses better social interactions with peers or has higher social proximity towards the user. Experiments conducted on Facebook and Twitter datasets exhibit the satisfying accuracy and encourage more advanced efforts on POI search.

Online social networks nowadays enjoy their worldwide prosperity, as they have revolutionized the way for people to discover, to share, and to distribute information. With millions of registered users and the proliferation of user-generated contents, the social networks become "giants", likely eligible to carry on any research tasks. However, the giants do have their Achilles Heel: extreme data sparsity. Compared with the massive data over the whole collection, individual posting documents, (e.g., a microblog less than 140 characters), seem to be too sparse to make a difference under various research scenarios, while actually they are different. In this paper we propose to tackle the Achilles Heel of social networks by smoothing the language model via influence propagation. We formulate a socialized factor graph model, which utilizes both the textual correlations between document pairs and the socialized augmentation networks behind the documents, such as user relationships and social interactions. These factors are modeled as attributes and dependencies among documents and their corresponding users. An efficient algorithm is designed to learn the proposed factor graph model. Finally we propagate term counts to smooth documents based on the estimated influence. Experimental results on Twitter and Weibo datasets validate the effectiveness of the proposed model. By leveraging the smoothed language model with social factors, our approach obtains significant improvement over several alternative methods on both intrinsic and extrinsic evaluations measured in terms of perplexity, nDCG and MAP results.

Location-based services allow users to perform check-in actions, which not only record their geo-spatial activities, but also provide a plentiful source for data scientists to analyze and plan more accurate and useful geographical recommender system. In this paper, we present a novel Time-aware Route Planning (TRP) problem using location check-in data. The central idea is that the pleasure of staying at the locations along a route is significantly affected by their visiting time. Each location has its own proper visiting time due to the category, objective, and population. To consider the visiting time of locations into route planning, we develop a three-stage time-aware route planning framework. First, since there is usually either noise time on existing locations or no visiting information on new locations constructed, we devise an inference method, LocTimeInf, to predict and recover the location visiting time on routes. Second, we aim to find the representative and popular time-aware location-transition behaviors from user check-in data, and a Time-aware Transit Pattern Mining (TTPM) algorithm is proposed correspondingly. Third, based on the mined time-aware transit patterns, we develop a Proper Route Search (PR-Search) algorithm to construct the final time-aware routes for recommendation. Experiments on Gowalla check-in data exhibit the promising effectiveness and efficiency of the proposed methods, comparing to a series of competitors.

Location-based services allow users to perform geospatial recording actions, which facilitates the mining of the moving activities of human beings. This article proposes to recommend time-sensitive trip routes consisting of a sequence of locations with associated timestamps based on knowledge extracted from large-scale timestamped location sequence data (e.g., check-ins and GPS traces). We argue that a good route should consider (a) the popularity of places, (b) the visiting order of places, (c) the proper visiting time of each place, and (d) the proper transit time from one place to another. By devising a statistical model, we integrate these four factors into a route goodness function that aims to measure the quality of a route. Equipped with the route goodness, we recommend time-sensitive routes for two scenarios. The first is about constructing the route based on the user-specified source location with the starting time. The second is about composing the route between the specified source location and the destination location given a starting time. To handle these queries, we propose a search method, Guidance Search , which consists of a novel heuristic satisfaction function that guides the search toward the destination location and a backward checking mechanism to boost the effectiveness of the constructed route. Experiments on the Gowalla check-in datasets demonstrate the effectiveness of our model on detecting real routes and performing cloze test of routes, comparing with other baseline methods. We also develop a system TripRouter as a real-time demo platform.

Online social networks are mainly characterized by large-scale and heterogeneous semantic relationships. Unfortunately, for online social network services such as Facebook or Twitter, it is very difficult to obtain the fully observed network without privilege to access the data internally. To address the above needs, social network sampling is a means that aims at identifying a representative sub graph that preserves certain properties of the network, given the information of any instance in the network is unknown before being sampled. This study tackles heterogeneous network sampling by considering the conditional dependency of node types and link types, where we design a property, Relational Profile, to account such characterization. We further propose a sampling method to preserve this property. Lastly, we propose to evaluate our model from three different angles. First, we show that the proposed sampling method can more faithfully preserve the Relational Profile. Second, we evaluate the usefulness of the Relational Profile showing such information is beneficial for link prediction tasks. Finally, we evaluate whether the networks sampled by our method can be used to train more accurate prediction models comparing to networks produced by other methods.

Graph mining is a popular technique for discovering the hidden structures or important instances in a graph, but the computational efficiency is usually a cause for concern when dealing with large-scale graphs containing billions of entities. Cloud computing is widely regarded as a feasible solution to the problem. In this work, we present an open source graph mining library called the MapReduce Graph Mining Framework (MGMF) to be a robust and efficient MapReduce-based graph mining tool. We start from dividing graph mining algorithms into four categories and designing a MapReduce framework for algorithms in each category. The experimental results show that MGMF is 3 to 20 times more efficient than PEGASUS, a state-of-the-art library for graph mining on MapReduce. Moreover, it provides better coverage of different graph mining algorithms. We also validate our framework on billion-scaled networks to demonstrate that it is scalable to the number of machines. Fur-thermore, we test and compare the feasibility between single ma-chine and the cloud computing technique. The effects of different file input formats for MapReduce are investigated as well. Our implemented open-source library can be downloaded from http://mslab.csie.ntu.edu.tw/~noahsark/MGMF/.

One important function of current social networking services is allowing users to initialize different kinds of activity groups (e.g. study group, cocktail party, and group buying) and invite friends to attend in either manual or collaborative manners. However, such process of group formation is tedious, and could either include inappropriate group members or miss relevant ones. This work proposes to automatically compose the activity groups in a social network according to user-specified activity information. Given the activity host, a set of labels representing the activity's subjects, the desired group size, and a set of must-inclusive persons, we aim to find a set of individuals as the activity group, in which members are required to not only be familiar with the host but also have great communications with each other. We devise an approximation algorithm to greedily solve the group composing problem. Experiments on a real social network show the promising effectiveness of the proposed approach as well as the satisfactory human subjective study.

This paper demonstrates a system that exploits graph mining, social network analysis, and agent-based crowd simulation techniques to investigate the evacuation dynamics during fire emergency. We create a novel evacuation planning system, EvaPlanner, to deal with three tasks. First, the system identifies the preferable locations to establish the exits to facilitate efficient evacuation from the dangerous areas. Second, it determines the most effective positions to place the emergency signs such that panic crowd can quickly find the exits. Third, it faithfully simulates the evacuation dynamics of crowd considering not only the individual movement kinetics but also the social connections between people. EvaPlanner provides a flexible experimental platform for investigating the evacuation dynamics under a variety of settings, and can further be utilized for animation and movie production. In addition, it can serve as a tool to assist architects address the safety concern during the planning phase. The demo system can be found in the link: http://mslab.csie.ntu.edu.tw/evaplanner/

Micro-blogging is a type of social networking service that has become ubiquitous in Web 2.0 era. Micro-blogs allows bloggers to exchange information, discuss ideas, and share experiences with friends or even strangers with similar interests. In this paper, we try to identify ways to measure how information is propagated in micro-blogs. More specifically, we consider the following issues. (1) How to quantify a person's capability to disseminate ideas via a micro-blog. (2) How to measure the extent of propagation of a concept in a micro-blog. (3) How to demonstrate and visualize information propagation in a micro-blog. We propose methods to effectively measure each user's ability to disseminate information via micro-blogs. The design of the measure considers three factors: (a) the number of people influenced, (b) the speed of propagation, and (c) the geographic distance of the propagation. We also provide an online demonstration micro-blog system that allows the users to explore the information propagation. The system shows the propagation paths and social graphs, influence scores, timelines, and geographical information among people for the user-given terms.

In online social networking services, there are a range of scenarios in which users want to search a particular person given the targeted person one's name. The challenge of such people search is namesake, which means that there are many people possess the same names in the social network. In this paper, we propose to leverage the query contexts to tackle such problems. For example, given the information of one's graduation year and city, the last names of some individuals, one may wish to find classmates from his/her high school. We formulate such problem as the context-based people search. Given a social network in which each node is associated with a set of labels and given a query set of labels consisting of a targeted name label and other context labels, our goal is to return a ranking list of persons who possess the targeted name label and connects to other context labels with minimum communication costs through an effective subgraph in the social network. We consider the interactions among query labels to propose a grouping-based method to solve the context-based people search. Our method consists of three major parts. First, we model those nodes with query labels into a group graph which is able to reduce the search space to enhance the time efficiency. Second, we identify three different kinds of connectors which connecting different groups, and exploit connectors to find the corresponding detailed graph topology from the group graph. Third, we propose a Connector-Steiner Tree algorithm to retrieve a resulting ranked list of individuals who possess the targeted label. Experimental results on the DBLP bibliography data show that our grouping-based method can reach the good quality of returned persons as a greedy search algorithm at a considerable outperformance on the time efficiency.

This work combines the central ideas from two different areas, crowd simulation and social network analysis, to tackle some existing problems in both areas from a new angle. We present a novel spatio-temporal social crowd simulation framework, Social Flocks, to revisit three essential research problems, (a) generation of social networks, (b) community detection in social networks, (c) modeling collective social behaviors in crowd simulation. Our framework produces social networks that satisfy the properties of high clustering coefficient, low average path length, and power-law degree distribution. It can also be exploited as a novel dynamic model for community detection. Finally our framework can be used to produce real-life collective social behaviors over crowds, including community-guided flocking, leader following, and spatio-social information propagation. Social Flocks can serve as visualization of simulated crowds for domain experts to explore the dynamic effects of the spatial, temporal, and social factors on social networks. In addition, it provides an experimental platform of collective social behaviors for social gaming and movie animations. Social Flocks demo is at http://mslab.csie.ntu.edu.tw/socialflocks/ .

Social networking services possess two features: (1) capturing the social relationships among people, represented by the social network, and (2) allowing users to express their preferences on different kinds of items (e.g. photo, celebrity, pages) through endorsing buttons, represented by a kind of endorsement bipartite graph. In this work, using such information, we propose a novel recommendation method, which leverages the viral marketing in the social network and the wisdom of crowds from endorsement network. Our recommendation consists of two parts. First, given some query terms describing user's preference, we find a set of targeted influencers who have the maximum activation probability on those nodes related to the query terms in the social network. Second, based on the derived targeted influencers as key experts, we recommend items via the endorsement network. We conduct the experiments on DBLP co-authorship social network with author-reference data as the endorsement network. The results show our method can achieve effective recommendations.

In an organization, based on the positions of employees there is usually an existing hierarchy among them. However, in real-life cases, people's interactions tend to form a certain communication structure due to some external forces or personal factors. In this paper, we aim at discovering the potential communication structure, in which nodes are typed labels (e.g. job-titles) and edges stand for tight interactions between typed labels in an organizational social network. To tackle this problem, we propose to exploit the concept of information asymmetry to model the core-periphery property in the communication structure. The proximity asymmetry is defined to realize the information asymmetry. We also devise two random-walk methods to calculate the proximity asymmetry between typed labels. The experiments conducted on the Enron email dataset shows that the proposed method outperforms some heuristic ones.

Micro-blogging services provide platforms for users to share their feelings and ideas on the go. Desiging to produce information stream in almost Micro-blogging services, although are capable of recording rich and diverse senses, still suffer from a drawback of not being able to provide deeper and summarized views. In this paper, we present a novel framework, Pusic, to musicalize micro-blogging messages for terms or users. Pusic can be used to (1) summarize users' messages into certain expression of emotions, (2) explore the emotions and senses and transform them into music, and (3) serve as a presentation of crowd net art. We generate the music from two aspects: emotion and harmony. The former is tackled by emotion detection from messages while the latter is estabilished by rule-based harmonic heuristics according to the detected emotions. Pusic has been announced online for people's experience and further investigation.

Social network is a powerful data structure that allows the depiction of relationship information between entities. However, real-world social networks are sometimes too complex for human to pursue further analysis. In this work, an unsupervised mechanism is proposed for egocentric information abstraction in heterogeneous social networks. To achieve this goal, we propose a vector space representation for heterogeneous social networks to identify linear combination of relations as features and compute statistical dependencies as feature values. Then we design several abstraction criteria to distill representative and important information to construct the abstracted graphs for visualization. The evaluations conducted on a real world movie dataset and an artificial crime dataset demonstrate that the abstractions can indeed retain important information and facilitate more accurate and efficient human analysis.