Few-shot relational learning on knowledge graph (KGs) aims to perform reasoning over relations with only a few training examples.While current methods have focused primarily on leveraging specific relational information, rich semantics inherent in KGs have been largely overlooked.To bridge this gap, we propose PromptMeta, a novel prompted metalearning framework that seamlessly integrates meta-semantics with relational information for few-shot relational learning.PromptMeta introduces two core innovations: (1) a Meta-Semantic Prompt (MSP) pool that learns and consolidates high-level meta-semantics shared across tasks, enabling effective knowledge transfer and adaptation to newly emerging relations; and (2) a learnable fusion mechanism that dynamically combines meta-semantics with task-specific relational information tailored to different few-shot tasks.Both components are optimized jointly with model parameters within a meta-learning framework.Extensive experiments and analyses on two realworld KG benchmarks validate the effectiveness of PromptMeta in adapting to new relations with limited supervision.

Few-shot knowledge graph relational learning seeks to perform reasoning over relations given only a limited number of training examples. While existing approaches largely adopt a meta-learning framework for enabling fast adaptation to new relations, they suffer from two key pitfalls. First, they learn relation meta-knowledge in isolation, failing to capture common relational patterns shared across tasks. Second, they struggle to effectively incorporate local, task-specific contexts crucial for rapid adaptation. To address these limitations, we propose MoEMeta, a novel meta-learning framework that disentangles globally shared knowledge from task-specific contexts to enable both effective model generalization and rapid adaptation. MoEMeta introduces two key innovations: (i) a mixture-of-experts (MoE) model that learns globally shared relational prototypes to enhance generalization, and (ii) a task-tailored adaptation mechanism that captures local contexts for fast task-specific adaptation. By balancing global generalization with local adaptability, MoEMeta significantly advances few-shot relational learning. Extensive experiments and analyses on three KG benchmarks show that MoEMeta consistently outperforms existing baselines, achieving state-of-the-art performance.

Abstract Entity alignment (EA) aims at identifying equivalent entity pairs across different knowledge graphs (KGs) that refer to the same real-world identity. It has been a compelling but challenging task that requires the integration of heterogeneous information from different KGs to expand the knowledge coverage and enhance inference abilities. To circumvent the shortage of prior seed alignments provided for training, recent EA models utilize pseudo-labeling strategies to iteratively add unaligned entity pairs predicted with high confidence to the seed alignments for model training. However, the adverse impact of confirmation bias during pseudo-labeling has been largely overlooked, thus hindering entity alignment performance. To systematically combat confirmation bias, we propose a new Unified Pseudo-Labeling framework for Entity Alignment (UPL-EA) that explicitly alleviates pseudo-labeling errors to boost the performance of entity alignment. UPL-EA achieves this goal through two key innovations: (1) Optimal Transport (OT)-based pseudo-labeling uses discrete OT modeling as an effective means to determine entity correspondences and reduce erroneous matches across two KGs. An effective criterion is derived to infer pseudo-labeled alignments that satisfy one-to-one correspondences; (2) Parallel pseudo-label ensembling refines pseudo-labeled alignments by combining predictions over multiple models independently trained in parallel. The ensembled pseudo-labeled alignments are thereafter used to augment seed alignments to reinforce subsequent model training for alignment inference. The effectiveness of UPL-EA in eliminating pseudo-labeling errors is both theoretically supported and experimentally validated. Our extensive results and in-depth analyses demonstrate the superiority of UPL-EA over 15 competitive baselines and its utility as a general pseudo-labeling framework for entity alignment.

Graph Neural Networks (GNNs) have emerged as powerful tools for analyzing graph-structured data, but their widespread adoption in critical applications is hindered by inherent biases related to sensitive attributes such as gender and race. While existing debiasing approaches typically focus on either modifying input graphs or incorporating fairness constraints into model objectives, we propose Fair Sparse GNN (FS-GNN), a novel framework that simultaneously enhances fairness and efficiency through joint sparsification of both input graphs and model architectures. Our approach iteratively identifies and removes less informative edges from input graphs while pruning redundant weights from the GNN model, guided by carefully designed fairness-aware objective functions. Through extensive experiments on real-world datasets, we demonstrate that FS-GNN achieves superior fairness metrics (reducing Statistical Parity from 7.94 to 0.6) while maintaining competitive prediction accuracy compared to state-of-the-art methods. Additionally, our theoretical analysis reveals distinct fairness implications of graph versus architecture sparsification, providing insights for future fairness-aware GNN designs. The proposed method not only advances fairness in GNNs but also offers substantial computational benefits through reduced model complexity, with FLOPs reductions ranging from 24% to 67%.

Alzheimer's Disease (AD), characterized by significant cognitive and functional impairment, necessitates the development of early detection techniques.Traditional diagnostic practices, such as cognitive assessments and biomarker analysis, are often invasive and costly.Deep learning-based approaches for non-invasive AD detection have been explored in recent studies, but the lack of accessible data hinders further improvements in detection performance.To address these challenges, we propose a novel semantic perturbation-based data augmentation method that essentially differs from existing techniques, which primarily rely on explicit data engineering.Our approach generates controlled semantic perturbations to enhance textual representations, aiding the model in identifying AD-specific linguistic patterns, particularly in scenarios with limited data availability.It learns contextual information and dynamically adjusts the perturbation degree for different linguistic features.This enhances the model's sensitivity to AD-specific linguistic features and its robustness against natural language noise.Experimental results on the ADReSS challenge dataset demonstrate that our approach outperforms other strong and competitive deep learning methods.

Abstract Graph neural networks (GNNs) have achieved state-of-the-art results for semi-supervised node classification on graphs. Nevertheless, the challenge of how to effectively learn GNNs with very few labels is still under-explored. As one of the prevalent semi-supervised methods, pseudo-labeling has been proposed to explicitly address the label scarcity problem. It is the process of augmenting the training set with pseudo-labeled unlabeled nodes to retrain a model in a self-training cycle. However, the existing pseudo-labeling approaches often suffer from two major drawbacks. First, these methods conservatively expand the label set by selecting only high-confidence unlabeled nodes without assessing their informativeness. Second, these methods incorporate pseudo-labels to the same loss function with genuine labels, ignoring their distinct contributions to the classification task. In this paper, we propose a novel informative pseudo-labeling framework (InfoGNN) to facilitate learning of GNNs with very few labels. Our key idea is to pseudo-label the most informative nodes that can maximally represent the local neighborhoods via mutual information maximization. To mitigate the potential label noise and class-imbalance problem arising from pseudo-labeling, we also carefully devise a generalized cross entropy with a class-balanced regularization to incorporate pseudo-labels into model retraining. Extensive experiments on six real-world graph datasets validate that our proposed approach significantly outperforms state-of-the-art baselines and competitive self-supervised methods on graphs.

Abstract Deep Neural Networks (DNNs) have recently achieved great success in many classification tasks. Unfortunately, they are vulnerable to adversarial attacks that generate adversarial examples with a small perturbation to fool DNN models, especially in model sharing scenarios. Adversarial training is proved to be the most effective strategy that injects adversarial examples into model training to improve the robustness of DNN models against adversarial attacks. However, adversarial training based on the existing adversarial examples fails to generalize well to standard, unperturbed test data. To achieve a better trade-off between standard accuracy and adversarial robustness, we propose a novel adversarial training framework called LAtent bounDary-guided aDvErsarial tRaining (LADDER) that adversarially trains DNN models on latent boundary-guided adversarial examples. As opposed to most of the existing methods that generate adversarial examples in the input space, LADDER generates a myriad of high-quality adversarial examples through adding perturbations to latent features. The perturbations are made along the normal of the decision boundary constructed by an SVM with an attention mechanism. We analyze the merits of our generated boundary-guided adversarial examples from a boundary field perspective and visualization view. Extensive experiments and detailed analysis on MNIST, SVHN, CelebA, and CIFAR-10 validate the effectiveness of LADDER in achieving a better trade-off between standard accuracy and adversarial robustness as compared with vanilla DNNs and competitive baselines.

Link prediction aims to infer the link existence between pairs of nodes in networks/graphs. Despite their wide application, the success of traditional link prediction algorithms is hindered by three major challenges—link sparsity,node attribute noiseanddynamic changes—that are faced by many real-world networks. To address these challenges, we propose aContextualizedSelf-SupervisedLearning (CSSL) framework that fully exploits structural context prediction for link prediction. The proposed CSSL framework learns a link encoder to infer the link existence probability from paired node embeddings, which are constructed via a transformation on node attributes. To generate informative node embeddings for link prediction, structural context prediction is leveraged as a self-supervised learning task to boost the link prediction performance. Two types of structural context are investigated,i.e., context nodes collected from random walksvs.context subgraphs. The CSSL framework can be trained in an end-to-end manner, with the learning of model parameters supervised by both the link prediction and self-supervised learning tasks. The proposed CSSL is a generic and flexible framework in the sense that it can handle both attributed and non-attributed networks, and operate under both transductive and inductive link prediction settings. Extensive experiments and ablation studies on seven real-world benchmark networks demonstrate the superior performance of the proposed self-supervision based link prediction algorithm over state-of-the-art baselines, on different types of networks under both transductive and inductive settings. The proposed CSSL also yields competitive performance in terms of its robustness to node attribute noise and scalability over large-scale networks.

Entity alignment aims to discover unique equivalent entity pairs with the same meaning across different knowledge graphs (KGs). Existing models have focused on projecting KGs into a latent embedding space so that inherent semantics between entities can be captured for entity alignment. However, the adverse impacts of alignment conflicts have been largely overlooked during training, thereby limiting the entity alignment performance. To address this issue, we propose a novel Conflict-aware Pseudo Labeling via Optimal Transport model (CPL-OT) for entity alignment. The key idea is to iteratively pseudo-label alignment pairs empowered with conflict-aware optimal transport (OT) modeling to boost the precision of entity alignment. CPL-OT is composed of two key components—entity embedding learning with global-local aggregation and iterative conflict-aware pseudo labeling—that mutually reinforce each other. To mitigate alignment conflicts during pseudo labeling, we propose to use optimal transport as an effective means to warrant one-to-one entity alignment between two KGs with the minimal overall transport cost. Extensive experiments on benchmark datasets validate the superiority of CPL-OT over state-of-the-art baselines under both settings with and without prior alignment seeds.

Traditional network embedding primarily focuses on learning a continuous vector representation for each node, preserving network structure and/or node content information, such that off-the-shelf machine learning algorithms can be easily applied to the vector-format node representations for network analysis. However, the learned continuous vector representations are inefficient for large-scale similarity search, which often involves finding nearest neighbors measured by distance or similarity in a continuous vector space. In this article, we propose a search efficient binary network embedding algorithm called BinaryNE to learn a binary code for each node, by simultaneously modeling node context relations and node attribute relations through a three-layer neural network. BinaryNE learns binary node representations using a stochastic gradient descent-based online learning algorithm. The learned binary encoding not only reduces memory usage to represent each node, but also allows fast bit-wise comparisons to support faster node similarity search than using Euclidean or other distance measures. Extensive experiments and comparisons demonstrate that BinaryNE not only delivers more than 25 times faster search speed, but also provides comparable or better search quality than traditional continuous vector based network embedding methods. The binary codes learned by BinaryNE also render competitive performance on node classification and node clustering tasks. The source code of the BinaryNE algorithm is available at https://github.com/daokunzhang/BinaryNE.

Active learning (AL) on attributed graphs has received increasing attention with the prevalence of graph-structured data. Although AL has been widely studied for alleviating label sparsity issues with the conventional nonrelational data, how to make it effective over attributed graphs remains an open research question. Existing AL algorithms on node classification attempt to reuse the classic AL query strategies designed for nonrelational data. However, they suffer from two major limitations. First, different AL query strategies calculated in distinct scoring spaces are often naively combined to determine which nodes to be labeled. Second, the AL query engine and the learning of the classifier are treated as two separating processes, resulting in unsatisfactory performance. In this article, we propose a SEmisupervised Adversarial active Learning (SEAL) framework on attributed graphs, which fully leverages the representation power of deep neural networks and devises a novel AL query strategy for node classification in an adversarial way. Our framework learns two adversarial components; a graph embedding network that encodes both the unlabeled and labeled nodes into a common latent space, expecting to trick the discriminator to regard all nodes as already labeled, and a semisupervised discriminator network that distinguishes the unlabeled from the existing labeled nodes. The divergence score, generated by the discriminator in a unified latent space, serves as the informativeness measure to actively select the most informative node to be labeled by an oracle. The two adversarial components form a closed loop to mutually and simultaneously reinforce each other toward enhancing the AL performance. Extensive experiments on real-world networks validate the effectiveness of the SEAL framework with superior performance improvements to state-of-the-art baselines on node classification tasks.

With the widespread use of information technologies, information networks are becoming increasingly popular to capture complex relationships across various disciplines, such as social networks, citation networks, telecommunication networks, and biological networks. Analyzing these networks sheds light on different aspects of social life such as the structure of societies, information diffusion, and communication patterns. In reality, however, the large scale of information networks often makes network analytic tasks computationally expensive or intractable. Network representation learning has been recently proposed as a new learning paradigm to embed network vertices into a low-dimensional vector space, by preserving network topology structure, vertex content, and other side information. This facilitates the original network to be easily handled in the new vector space for further analysis. In this survey, we perform a comprehensive review of the current literature on network representation learning in the data mining and machine learning field. We propose new taxonomies to categorize and summarize the state-of-the-art network representation learning techniques according to the underlying learning mechanisms, the network information intended to preserve, as well as the algorithmic designs and methodologies. We summarize evaluation protocols used for validating network representation learning including published benchmark datasets, evaluation methods, and open source algorithms. We also perform empirical studies to compare the performance of representative algorithms on common datasets, and analyze their computational complexity. Finally, we suggest promising research directions to facilitate future study.

For the classification of sequential data, dynamic Bayesian networks and recurrent neural networks (RNNs) are the preferred models. While the former can explicitly model the temporal dependences between the variables, and the latter have the capability of learning representations. The recurrent temporal restricted Boltzmann machine (RTRBM) is a model that combines these two features. However, learning and inference in RTRBMs can be difficult because of the exponential nature of its gradient computations when maximizing log likelihoods. In this article, first, we address this intractability by optimizing a conditional rather than a joint probability distribution when performing sequence classification. This results in the "sequence classification restricted Boltzmann machine" (SCRBM). Second, we introduce gated SCRBMs (gSCRBMs), which use an information processing gate, as an integration of SCRBMs with long short-term memory (LSTM) models. In the experiments reported in this article, we evaluate the proposed models on optical character recognition, chunking, and multiresident activity recognition in smart homes. The experimental results show that gSCRBMs achieve the performance comparable to that of the state of the art in all three tasks. gSCRBMs require far fewer parameters in comparison with other recurrent networks with memory gates, in particular, LSTMs and gated recurrent units (GRUs).

Sharing a pre-trained machine learning model, particularly a deep neural network via prediction APIs, is becoming a common practice on machine learning as a service (MLaaS) platforms nowadays. Although deep neural networks (DNN) have shown remarkable successes in many tasks, they are also criticized for the lack of interpretability and transparency. Interpreting a shared DNN model faces two additional challenges compared with interpreting a general model. (1) Limited training data can be disclosed to users. (2) The internal structure of the models may not be available. These two challenges impede the application of most existing interpretability approaches, such as saliency maps or influence functions, for DNN models. Case-based reasoning methods have been used for interpreting decisions; however, how to select and organize the data points under the constraints of shared DNN models is not discussed. Moreover, simply providing cases as explanations may not be sufficient for supporting instance level interpretability. Meanwhile, existing interpretation methods for DNN models generally lack the means to evaluate the reliability of the interpretation. In this article, we propose a framework named Shared Model INTerpreter (SMINT) to address the above limitations. We propose a new data structure called a boundary graph to organize training points to mimic the predictions of DNN models. We integrate local features, such as saliency maps and interpretable input masks, into the data structure to help users to infer the model decision boundaries. We show that the boundary graph is able to address the reliability issues in many local interpretation methods. We further design an algorithm named hidden-layer aware p-test to measure the reliability of the interpretations. Our experiments show that SMINT is able to achieve above 99% fidelity to corresponding DNN models on both MNIST and ImageNet by sharing only a tiny fraction of training data to make these models interpretable. The human pilot study demonstrates that SMINT provides better interpretability compared with existing methods. Moreover, we demonstrate that SMINT is able to assist model tuning for better performance on different user data.

We study the problem of selecting a subset of weakly labeled data where the labels of each data instance are redundant and imperfect. In real applications, less-than-expert labels are obtained at low cost in order to acquire many labels for each instance and then used for estimating the ground truth. However, on one side, preparing and processing data itself sometimes can be even more expensive than labeling. On the other side, noisy labels also decrease the performance of supervised learning methods. Thus, we introduce a new quality control mechanism on labels for each instance and use it to select an optimal subset of data. Based on the quality control mechanism, in which the labeling quality of each instance is estimated, it provides a way to know which instance has enough reliable labels or how many labels still need to be collected for a data instance. In this paper, first, we consider the data subset selection problem under the probably approximately correct model. Then, we show how to find an ϵ -optimal labeled instance based on expected labeling quality. Furthermore, we propose new algorithms to select the best k quality instances that have high expected labeling quality. Using a reliable subset of data provides substantial benefit over using all data with imperfect multiple labels, and the expected labeling quality is a good indicator of where to allocate labeling effort. It shows how many labels should be acquired for an instance and which instances are qualified to be selected comparing with others. Both the theoretical guarantees and the comprehensive experiments demonstrate the effectiveness and efficiency of our algorithms.

Attributed network embedding aims to learn low-dimensional vector representations for nodes in a network, where each node contains rich attributes/features describing node content. Because network topology structure and node attributes often exhibit high correlation, incorporating node attribute proximity into network embedding is beneficial for learning good vector representations. In reality, large-scale networks often have incomplete/missing node content or linkages, yet existing attributed network embedding algorithms all operate under the assumption that networks are complete. Thus, their performance is vulnerable to missing data and suffers from poor scalability. In this paper, we propose a Scalable Incomplete Network Embedding (SINE) algorithm for learning node representations from incomplete graphs. SINE formulates a probabilistic learning framework that separately models pairs of node-context and node-attribute relationships. Different from existing attributed network embedding algorithms, SINE provides greater flexibility to make the best of useful information and mitigate negative effects of missing information on representation learning. A stochastic gradient descent based online algorithm is derived to learn node representations, allowing SINE to scale up to large-scale networks with high learning efficiency. We evaluate the effectiveness and efficiency of SINE through extensive experiments on real-world networks. Experimental results confirm that SINE outperforms state-of-the-art baselines in various tasks, including node classification, node clustering, and link prediction, under settings with missing links and node attributes. SINE is also shown to be scalable and efficient on large-scale networks with millions of nodes/edges and high-dimensional node features. The source code of this paper is available at https://github.com/daokunzhang/SINE.

During large-scale emergencies such as natural and man-made disasters, a massive amount of information is posted by the public in social media. Collecting, aggregating, and presenting this information to stakeholders can be extremely challenging, particularly if an understanding of the "big picture»» is sought. This international workshop, the fifth in the series, is a key venue for researchers and practitioners to discuss research challenges and technical issues around the usage of social media in disaster management. Workshop»s website: https://sites.google.com/site/swdm2018/

Despite outperforming humans in many tasks, deep neural network models are also criticized for the lack of transparency and interpretability in decision making. The opaqueness results in uncertainty and low confidence when deploying such a model in model sharing scenarios, where the model is developed by a third party. For a supervised machine learning model, sharing training process including training data is a way to gain trust and to better understand model predictions. However, it is not always possible to share all training data due to privacy and policy constraints. In this paper, we propose a method to disclose a small set of training data that is just sufficient for users to get the insight into a complicated model. The method constructs a boundary tree using selected training data and the tree is able to approximate the complicated deep neural network models with high fidelity. We show that data point pairs in the tree give users significantly better understanding of the model decision boundaries and paves the way for trustworthy model sharing.

BACKGROUND: Early and accurate identification of potential adverse drug reactions (ADRs) for combined medication is vital for public health. Existing methods either rely on expensive wet-lab experiments or detecting existing associations from related records. Thus, they inevitably suffer under-reporting, delays in reporting, and inability to detect ADRs for new and rare drugs. The current application of machine learning methods is severely impeded by the lack of proper drug representation and credible negative samples. Therefore, a method to represent drugs properly and to select credible negative samples becomes vital in applying machine learning methods to this problem. RESULTS: In this work, we propose a machine learning method to predict ADRs of combined medication from pharmacologic databases by building up highly-credible negative samples (HCNS-ADR). Specifically, we fuse heterogeneous information from different databases and represent each drug as a multi-dimensional vector according to its chemical substructures, target proteins, substituents, and related pathways first. Then, a drug-pair vector is obtained by appending the vector of one drug to the other. Next, we construct a drug-disease-gene network and devise a scoring method to measure the interaction probability of every drug pair via network analysis. Drug pairs with lower interaction probability are preferentially selected as negative samples. Following that, the validated positive samples and the selected credible negative samples are projected into a lower-dimensional space using the principal component analysis. Finally, a classifier is built for each ADR using its positive and negative samples with reduced dimensions. The performance of the proposed method is evaluated on simulative prediction for 1276 ADRs and 1048 drugs, comparing using four machine learning algorithms and with two baseline approaches. Extensive experiments show that the proposed way to represent drugs characterizes drugs accurately. With highly-credible negative samples selected by HCNS-ADR, the four machine learning algorithms achieve significant performance improvements. HCNS-ADR is also shown to be able to predict both known and novel drug-drug-ADR associations, outperforming two other baseline approaches significantly. CONCLUSIONS: The results demonstrate that integration of different drug properties to represent drugs are valuable for ADR prediction of combined medication and the selection of highly-credible negative samples can significantly improve the prediction performance.

This paper addresses social network embedding, which aims to embed social network nodes, including user profile information, into a latent low-dimensional space. Most of the existing works on network embedding only consider network structure, but ignore user-generated content that could be potentially helpful in learning a better joint network representation. Different from rich node content in citation networks, user profile information in social networks is useful but noisy, sparse, and incomplete. To properly utilize this information, we propose a new algorithm called User Profile Preserving Social Network Embedding (UPP-SNE), which incorporates user profile with network structure to jointly learn a vector representation of a social network. The theme of UPP-SNE is to embed user profile information via a nonlinear mapping into a consistent subspace, where network structure is seamlessly encoded to jointly learn informative node representations. Extensive experiments on four real-world social networks show that compared to state-of-the-art baselines, our method learns better social network representations and achieves substantial performance gains in node classification and clustering tasks.

Background: Smartphones have reached levels of popularity and penetration where they are now suitable for use in population health interventions. A key feature of smartphones is push notification or in app messaging service, which can be used to alert users to messages or instructions pertaining to an installed app. Little evidence exists as to the persuasive power of these messages.Method: We conducted a 24-week live user evaluation of push notifications used in a behavior-based mobile app for a meal replacement program to understand the role of push notifications in persuading users to engage with self-monitoring tasks.Results: User perception of the prompts were verified through questionnaires, which in conjunction with the interaction logs show that users were tolerant of multiple daily prompts. The decline in compliance to the tasks set, however, shows that while the participants did not object to receiving prompts, they were less likely to respond to them as the study progressed.Conclusions: Push notifications and user tasks are appropriate mechanisms to engage users with mobile technology in the short term.

This paper addresses the problem of active learning on multiple tasks, where labeled data are expensive to obtain for each individual task but the learning problems share some commonalities across multiple related tasks. To leverage the benefits of jointly learning from multiple related tasks and making active queries, we propose a novel active multitask learning approach based on trace norm regularized least squares. The basic idea is to induce an optimal classifier which has the lowest risk and at the same time which is closest to the true hypothesis. Toward this aim, we devise a new active selection criterion that takes into account not only the risk but also the excess risk, which measures the distance to the true hypothesis. Based on this criterion, our proposed algorithm actively selects the instance to query for its label based on the combination of the two risks. Experiments on both synthetic and real-world datasets show that our proposed algorithm provides superior performance as compared to other state-of-the-art active learning methods.

A cascade classifier has turned out to be effective insliding-window based real-time object detection. In acascade classifier, node learning is the key process,which includes feature selection and classifier design. Previous algorithms fail to effectively tackle the asymmetry and intersection problems existing in cascade classification, thereby limiting the performance of object detection. In this paper, we improve current feature selection algorithm by addressing both asymmetry and intersection problems. We formulate asymmetric feature selection as a submodular function maximization problem. We then propose a new algorithm SAFS with formal performance guarantee to solve this problem.We use face detection as a case study and perform experiments on two real-world face detection datasets. The experimental results demonstrate that our algorithm SAFS outperforms the state-of-art feature selection algorithms in cascade object detection, such as FFS and LACBoost.

The proliferation of social media platforms together with the wide adoption of smartphone devices has transformed how we communicate and share news. During large-scale emergencies, such as natural disasters or armed attacks, victims, responders, and volunteers increasingly use social media to post situation updates and to request and offer help. The use of social media for emergency and disaster response has been a prominent application of information and knowledge management techniques in recent years. There are a number of challenges associated with near real-time processing of vast volumes of information in a way that makes sense for people directly affected, for volunteer organizations, and for official emergency response agencies. As massive amount of messages posted by users are transformed into semi-structured records via information extraction and natural language processing techniques, there is a growing need for developing advanced techniques to aggregate this large-scale data to gain an understanding of the ``big picture'' of an emergency, and to detect and predict how a disaster could develop. This workshop seeks to provide a platform for the exchange of ideas, identification of important problems, and discovery of possible synergies. It will enable interesting discussions and encouraged collaboration between various disciplines, and information and knowledge management approaches is the core of this workshop.

We address the problem of classifying sparsely labeled networks, where labeled nodes in the network are extremely scarce. Existing algorithms, such as collective classification, have been shown to be effective for jointly deriving labels of related nodes, by exploiting class label dependencies among neighboring nodes. However, when the underlying network is sparsely labeled, most nodes have too few or even no connections to labeled nodes. This makes it very difficult to leverage supervised knowledge from labeled nodes to accurately estimate label dependencies, thereby largely degrading the classification accuracy. In this paper, we propose a novel discriminative matrix factorization (DMF) based algorithm that effectively learns a latent network representation by exploiting topological paths between labeled and unlabeled nodes, in addition to nodes' content information. The main idea is to use matrix factorization to obtain a compact representation of the network that fully encodes nodes' content information and network structure, and unleash discriminative power inferred from labeled nodes to directly benefit collective classification. To achieve this, we formulate a new matrix factorization objective function that integrates network representation learning with an empirical loss minimization for classifying node labels. An efficient optimization algorithm based on conjugate gradient methods is proposed to solve the new objective function. Experimental results on real-world networks show that DMF yields superior performance gain over the state-of-the-art baselines on sparsely labeled networks.

In this paper, we present a novel transfer learning framework for network node classification. Our objective is to accurately predict node labels in a target network by leveraging information from an auxiliary source network. Such a transfer learning framework is potentially useful for broader areas of network classification, where emerging new networks might not have sufficient labeled information because node labels are either costly to obtain or simply not available, whereas many established networks from related domains are available to benefit the learning. In reality, the source and the target networks may not share common nodes or connections, so the major challenge of cross-network transfer learning is to identify knowledge/patterns transferable between networks and potentially useful to support cross-network learning. In this work, we propose to learn common signature subgraphs between networks, and use them as structure features for the target network. By combining the original node content features and the new structure features, we develop an iterative classification algorithm, TrGraph, that utilizes label dependency to jointly classify nodes in the target network. Experiments on real-world networks demonstrate that TrGraph achieves the superior performance compared to the state-of-the-art baseline methods.

Advances in social networking and communication technologies have witnessed an increasing number of applications where data is not only characterized by rich content information, but also connected with complex relationships representing social roles and dependencies between individuals. To enable knowledge discovery from such networked data, network representation learning (NRL) aims to learn vector representations for network nodes, such that off-the-shelf machine learning algorithms can be directly applied. To date, existing NRL methods either primarily focus on network structure or simply combine node content and topology for learning. We argue that in information networks, information is mainly originated from three sources: (1) homophily, (2) topology structure, and (3) node content. Homophily states social phenomenon where individuals sharing similar attributes (content) tend to be directly connected through local relational ties, while topology structure emphasizes more on global connections. To ensure effective network representation learning, we propose to augment three information sources into one learning objective function, so that the interplay roles between three parties are enforced by requiring the learned network representations (1) being consistent with node content and topology structure, and also (2) following the social homophily constraints in the learned space. Experiments on multi-class node classification demonstrate that the representations learned by the proposed method consistently outperform state-of-the-art NRL methods, especially for very sparsely labeled networks.

In recent years, many studies have been published on data collected from social media, especially microblogs such as Twitter. However, rather few of these studies have considered evaluation methodologies that take into account the statistically dependent nature of such data, which breaks the theoretical conditions for using cross-validation. Despite concerns raised in the past about using cross-validation for data of similar characteristics, such as time series, some of these studies evaluate their work using standard k-fold cross-validation. Through experiments on Twitter data collected during a two-year period that includes disastrous events, we show that by ignoring the statistical dependence of the text messages published in social media, standard cross-validation can result in misleading conclusions in a machine learning task. We explore alternative evaluation methods that explicitly deal with statistical dependence in text. Our work also raises concerns for any other data for which similar conditions might hold.

In this paper, we present a novel transfer learning framework for network node classification. Our objective is to accurately predict the labels of nodes in a target network by leveraging information from an auxiliary source network. Such a transfer learning framework is potentially useful for broader areas of network classification, where emerging new networks might not have sufficient labeled information because node labels are either costly to obtain or simply not available, whereas many established networks from related domains are available to benefit the learning. In reality, the source and the target networks may not share common nodes or connections, so the major challenge of cross-network transfer learning is to identify knowledge/patterns transferable between networks and potentially useful to support cross-network learning. In this work, we propose to learn common signature subgraphs between networks, and use them to construct new structure features for the target network. By combining the original node content features and the new structure features, we develop an iterative classification algorithm, TrGraph, that utilizes label dependency to jointly classify nodes in the target network. Experiments on real-world networks demonstrate that TrGraph achieves the superior performance compared to the state-of-the-art baseline methods, and transferring generalizable structure information can indeed improve the node classification accuracy.

This paper studies the active learning problem in crowdsourcing settings, where multiple imperfect annotators with varying levels of expertise are available for labeling the data in a given task. Annotations collected from these labelers may be noisy and unreliable, and the quality of labeled data needs to be maintained for data mining tasks. Previous solutions have attempted to estimate individual users' reliability based on existing knowledge in each task, but for this to be effective each task requires a large quantity of labeled data to provide accurate estimates. In practice, annotation budgets for a given task are limited, so each instance can be presented to only a few users, each of whom can only label a few examples. To overcome data scarcity we propose a new probabilistic model that transfers knowledge from abundant unlabeled data in auxiliary domains to help estimate labelers' expertise. Based on this model we present a novel active learning algorithm that: a) simultaneously selects the most informative example and b) queries its label from the labeler with the best expertise. Experiments on both text and image datasets demonstrate that our proposed method outperforms other state-of-the-art active learning methods.

Modern information networks, such as social networks, are often characterized with large sizes and dynamic changing structures. To analyze these networks, existing solutions commonly rely on graph sampling techniques to reduce network sizes, and then carry out succeeding mining processes, such as labeling network nodes to build classification models. Such a sampling-then-labeling paradigm assumes that the whole network is available for sampling and the sampled network is useful for all subsequent tasks (such as network classification). Yet real-world networks are rarely immediately available unless the sampling process progressively crawls every single node and its connections. Meanwhile, without knowing the underlying analytic objective, the sampled network can hardly produce quality results. In this paper, we propose an Active Exploration framework for large graphs where the goal is to carry out network sampling and node labeling at the same time. To achieve this goal, we consider a network as a Markov chain and compute its stationary distribution by using supervised random walks. The stationary distribution of the sampled network help identify important nodes to be explored in the next step, and the labeling process labels the most informative node which in turn strengthens the sampling process. The mutually and simultaneously enhanced sampling and labeling processes ensure that the final network contains a maximum number of nodes directly related to the underlying mining tasks.

This paper addresses the problem of transferring useful knowledge from a source network to predict node labels in a newly formed target network. While existing transfer learning research has primarily focused on vector-based data, in which the instances are assumed to be independent and identically distributed, how to effectively transfer knowledge across different information networks has not been well studied, mainly because networks may have their distinct node features and link relationships between nodes. In this paper, we propose a new transfer learning algorithm that attempts to transfer common latent structure features across the source and target networks. The proposed algorithm discovers these latent features by constructing label propagation matrices in the source and target networks, and mapping them into a shared latent feature space. The latent features capture common structure patterns shared by two networks, and serve as domain-independent features to be transferred between networks. Together with domain-dependent node features, we thereafter propose an iterative classification algorithm that leverages label correlations to predict node labels in the target network. Experiments on real-world networks demonstrate that our proposed algorithm can successfully achieve knowledge transfer between networks to help improve the accuracy of classifying nodes in the target network.

With the recent explosion of social network applications, active learning has increasingly become an important paradigm for classifying networked data. While existing research has shown promising results by exploiting network properties to improve the active learning performance, they are all based on a static setting where the number and the type of classes underlying the networked data remain stable and unchanged. For most social network applications, the dynamic change of users and their evolving relationships, along with the emergence of new social events, often result in new classes that need to be immediately discovered and labeled for classification. This paper proposes a novel approach called ADLNET for active class discovery and learning with networked data. Our proposed method uses the Dirichlet process defined over class distributions to enable active discovery of new classes, and explicitly models label correlations in the utility function of active learning. Experimental results on two real-world networked data sets demonstrate that our proposed approach outperforms other state-of-the-art methods.

During a disastrous event, such as an earthquake or river flooding, information on what happened, who was affected and how, where help is needed, and how to aid people who were affected, is crucial. While communication is important in such times of crisis, damage to infrastructure such as telephone lines makes it difficult for authorities and victims to communicate. Microblogging has played a critical role as an important communication platform during crises when other media has failed. We demonstrate our ESA (Emergency Situation Awareness) system that mines microblogs in real-time to extract and visualise useful information about incidents and their impact on the community in order to equip the right authorities and the general public with situational awareness.

Recent years have witnessed the growing popularity of sensor and sensor-network technologies, supporting important practical applications. One of the fundamental issues is how to accurately locate a user with few labeled data in a wireless sensor network, where a major difficulty arises from the need to label large quantities of user location data, which in turn requires knowledge about the locations of signal transmitters or access points. To solve this problem, we have developed a novel machine learning-based approach that combines collaborative filtering with graph-based semi-supervised learning to learn both mobile users' locations and the locations of access points. Our framework exploits both labeled and unlabeled data from mobile devices and access points. In our two-phase solution, we first build a manifold-based model from a batch of labeled and unlabeled data in an offline training phase and then use a weighted k-nearest-neighbor method to localize a mobile client in an online localization phase. We extend the two-phase colocalization to an online and incremental model that can deal with labeled and unlabeled data that come sequentially and adapt to environmental changes. Finally, we embed an action model to the framework such that additional kinds of sensor signals can be utilized to further boost the performance of mobile tracking. Compared to other state-of-the-art systems, our framework has been shown to be more accurate while requiring less calibration effort in our experiments performed on three different testbeds.

Positive and unlabelled learning (PU learning) has been investigated to deal with the situation where only the positive examples and the unlabelled examples are available. Most of the previous works focus on identifying some negative examples from the unlabelled data, so that the supervised learning methods can be applied to build a classifier. However, for the remaining unlabelled data, which can not be explicitly identified as positive or negative (we call them ambiguous examples), they either exclude them from the training phase or simply enforce them to either class. Consequently, their performance may be constrained. This paper proposes a novel approach, called similarity-based PU learning (SPUL) method, by associating the ambiguous examples with two similarity weights, which indicate the similarity of an ambiguous example towards the positive class and the negative class, respectively. The local similarity-based and global similarity-based mechanisms are proposed to generate the similarity weights. The ambiguous examples and their similarity-weights are thereafter incorporated into an SVM-based learning phase to build a more accurate classifier. Extensive experiments on real-world datasets have shown that SPUL outperforms state-of-the-art PU learning methods.

This paper presents a novel hybrid approach to outlier detection by incorporating local data uncertainty into the construction of a global classifier. To deal with local data uncertainty, we introduce a confidence value to each data example in the training data, which measures the strength of the corresponding class label. Our proposed method works in two steps. Firstly, we generate a pseudo training dataset by computing a confidence value of each input example on its class label. We present two different mechanisms: kernel k-means clustering algorithm and kernel LOF-based algorithm, to compute the confidence values based on the local data behavior. Secondly, we construct a global classifier for outlier detection by generalizing the SVDD-based learning framework to incorporate both positive and negative examples as well as their associated confidence values. By integrating local and global outlier detection, our proposed method explicitly handles the uncertainty of the input data and enhances the ability of SVDD in reducing the sensitivity to noise. Extensive experiments on real life datasets demonstrate that our proposed method can achieve a better tradeoff between detection rate and false alarm rate as compared to four state-of-the-art outlier detection algorithms.

Multiple instance learning (MIL) is a generalization of supervised learning which attempts to learn useful information from bags of instances. In MIL, the true labels of the instances in positive bags are not always available for training. This leads to a critical challenge, namely, handling the ambiguity of instance labels in positive bags. To address this issue, this paper proposes a novel MIL method named SMILE (Similarity-based Multiple Instance LEarning). It introduces a similarity weight to each instance in positive bag, which represents the instance similarity towards the positive and negative classes. The instances in positive bags, together with their similarity weights, are thereafter incorporated into the learning phase to build an extended SVM-based predictive classifier. Experiments on three real-world datasets consisting of 12 subsets show that SMILE achieves markedly better classification accuracy than state-of-the-art MIL methods.

Event detection is a critical task in sensor networks, especially for environmental monitoring applications. Traditional solutions to event detection are based on analyzing one-shot data points, which might incur a high false alarm rate because sensor data is inherently unreliable and noisy. To address this issue, we propose a novel Distributed Single-pass Incremental Clustering (DSIC) technique to cluster the time series obtained at sensor nodes based on their underlying trends. In order to achieve scalability and energy-efficiency, our DSIC technique uses a hierarchical structure of sensor networks as the underlying infrastructure. The algorithm first compresses the time series produced at individual sensor nodes into a compact representation using Haar wavelet transform, and then, based on dynamic time warping distances, hierarchically groups the approximate time series into a global clustering model in an incremental manner. Experimental results on both real data and synthetic data demonstrate that our DSIC algorithm is accurate, energy-efficient and robust with respect to network topology changes.

With the availability of affordable sensors and sensor networks, sensor-based human activity recognition has attracted much attention in artificial intelligence and ubiquitous computing. In this paper, we present a novel two-phase approach for detecting abnormal activities based on wireless sensors attached to a human body. Detecting abnormal activities is a particular important task in security monitoring and healthcare applications of sensor networks, among many others. Traditional approaches to this problem suffer from a high false positive rate, particularly when the collected sensor data are biased towards normal data while the abnormal events are rare. Therefore, there is a lack of training data for many traditional data mining methods to be applied. To solve this problem, our approach first employs a one-class support vector machine (SVM) that is trained on commonly available normal activities, which filters out the activities that have a very high probability of being normal. We then derive abnormal activity models from a general normal model via a kernel nonlinear regression (KNLR) to reduce false positive rate in an unsupervised manner. We show that our approach provides a good tradeoff between abnormality detection rate and false alarm rate, and allows abnormal activity models to be automatically derived without the need to explicitly label the abnormal training data, which are scarce. We demonstrate the effectiveness of our approach using real data collected from a sensor network that is deployed in a realistic setting.

In wireless networks, a client's locations can be estimated using the signals received from various signal transmitters. Static fingerprint-based techniques are commonly used for location estimation, in which a radio map is built by calibrating signal-strength values in the offline phase. These values, compiled into deterministic or probabilistic models, are used for online localization. However, the radio map can be outdated when the signal-strength values change with time due to environmental dynamics, and repeated data calibration is infeasible or expensive. In this paper, we present a novel algorithm, known as LEMT (Location Estimation using Model Trees), to reconstruct a radio map using real-time signal- strength readings received at the reference points. This algorithm can take into account real-time signal-strength values at each time point and make use of the dependency between the estimated locations and reference points. We show that this technique can effectively accommodate the variations of signal strength over different time periods without the need to rebuild the radio maps repeatedly. We demonstrate the effectiveness of our proposed technique on realistic data sets collected from an 802.11b wireless network and a RFID-based network.

A major issue of activity recognition in sensor networks is automatically recognizing a user's high-level goals accurately from low-level sensor data. Traditionally, solutions to this problem involve the use of a location-based sensor model that predicts the physical locations of a user from the sensor data. This sensor model is often trained offline, incurring a large amount of calibration effort. In this article, we address the problem using a goal-based segmentation approach, in which we automatically segment the low-level user traces that are obtained cheaply by collecting the signal sequences as a user moves in wireless environments. From the traces we discover primitive signal segments that can be used for building a probabilistic activity model to recognize goals directly. A major advantage of our algorithm is that it can reduce a significant amount of human effort in calibrating the sensor data while still achieving comparable recognition accuracy. We present our theoretical framework for activity recognition, and demonstrate the effectiveness of our new approach using the data collected in an indoor wireless environment.

Most data mining algorithms and tools stop at discovered customer models, producing distribution information on customer profiles. Such techniques, when applied to industrial problems such as customer relationship management (CRM), are useful in pointing out customers who are likely attritors and customers who are loyal, but they require human experts to postprocess the discovered knowledge manually. Most of the postprocessing techniques have been limited to producing visualization results and interestingness ranking, but they do not directly suggest actions that would lead to an increase in the objective function such as profit. In this paper, we present novel algorithms that suggest actions to change customers from an undesired status (such as attritors) to a desired one (such as loyal) while maximizing an objective function: the expected net profit. These algorithms can discover cost-effective actions to transform customers from undesirable classes to desirable ones. The approach we take integrates data mining and decision making tightly by formulating the decision making problems directly on top of the data mining results in a postprocessing step. To improve the effectiveness of the approach, we also present an ensemble of decision trees which is shown to be more robust when the training data changes. Empirical tests are conducted on both a realistic insurance application domain and UCI benchmark data

An important goal of indoor location estimation systems is to increase the estimation accuracy while reducing the power consumption. In this paper, we present a novel algorithm known as CaDet for power-efficient location estimation by intelligently selecting the number of access points (APs) used for location estimation. We show that by employing machine learning techniques, CaDet is able to use a small subset of the APs in the environment to detect a client's location with high accuracy. CaDet uses a combination of information theory, clustering analysis, and a decision tree algorithm. By collecting data and testing our algorithms in a realistic WLAN environment in the computer science department area of the Hong Kong University of Science and Technology, we show that CaDet (clustering and decision tree-based method) can be much higher in accuracy as compared to other methods. We also show through experiments that, by intelligently selecting APs, we are able to save the power on the client device while achieving the same level of accuracy.

Web-search queries are typically short and ambiguous. To classify these queries into certain target categories is a difficult but important problem. In this article, we present a new technique called query enrichment, which takes a short query and maps it to intermediate objects. Based on the collected intermediate objects, the query is then mapped to target categories. To build the necessary mapping functions, we use an ensemble of search engines to produce an enrichment of the queries. Our technique was applied to the ACM Knowledge Discovery and Data Mining competition (ACM KDDCUP) in 2005, where we won the championship on all three evaluation metrics (precision, F1 measure, which combines precision and recall, and creativity, which is judged by the organizers) among a total of 33 teams worldwide. In this article, we show that, despite the difficulty of an abundance of ambiguous queries and lack of training data, our query-enrichment technique can solve the problem satisfactorily through a two-phase classification framework. We present a detailed description of our algorithm and experimental evaluation. Our best result for F1 and precision is 42.4% and 44.4%, respectively, which is 9.6% and 24.3% higher than those from the runner-ups, respectively.

We present a novel approach for clustering sequences of multi-dimensional trajectory data obtained from a sensor network. The sensory time-series data present new challenges to data mining, including uneven sequence lengths, multi-dimensionality and high levels of noise. We adopt a principled approach, by first transforming all the data into an equal-length vector form while keeping as much temporal information as we can, and then applying dimensionality and noise reduction techniques such as spectral clustering to the transformed data. Experimental evaluation on synthetic and real data shows that our proposed approach outperforms standard model-based clustering algorithms for time series data.

In this paper, we present a novel method to adapt the temporal radio maps for indoor location estimation by off-setting the variational environmental factors using data mining techniques and reference points. Environmental variations, which cause the signals to change from time to time even at the same location, present a challenging task for indoor location estimation in the IEEE 802.11b infrastructure. In such a dynamic environment, the radio maps obtained in one time period may not be applicable in other time periods. To solve this problem, we apply a regression analysis to learn the temporal predictive relationship between the signal-strength values received by sparsely located reference points and that received by the mobile device. This temporal prediction model can then be used for online localization based on the newly observed signal-strength values at the client side and the reference points. We show that this technique can effectively accommodate the variations of signal-strength values over different time periods without the need to rebuild the radio maps repeatedly. We also show that the location of mobile device can be accurately determined using this technique with lower density in the distribution of the reference points.

Most data mining algorithms and tools stop at discovered customer models, producing distribution information on customer profiles. Such techniques, when applied to industrial problems such as customer relationship management (CRM), are useful in pointing out customers who are likely attritors and customers who are loyal, but they require human experts to postprocess the mined information manually. Most of the postprocessing techniques have been limited to producing visualization results and interestingness ranking, but they do not directly suggest actions that would lead to an increase the objective function such as profit. Here, we present a novel algorithm that suggest actions to change customers from an undesired status (such as attritors) to a desired one (such as loyal) while maximizing objective function: the expected net profit. We develop these algorithms under resource constraints that are abound in reality. The contribution of the work is in taking the output from an existing mature technique (decision trees, for example), and producing novel, actionable knowledge through automatic postprocessing.