Memory plays a central role in transforming Large Language Model (LLM)-based agents from reactive predictors into consistent, context-aware collaborators. While LLM-based single-agent memory has been extensively studied, memory in LLM-based Multi-Agent Systems (LLM-MAS) lacks a systematic taxonomy and review. In multi-agent contexts, memory becomes a shared cognitive infrastructure enabling collective intelligence, long-term coordination, and team evolvement. This survey provides the first comprehensive review of memory in LLM-MAS, synthesizing research across memory architectures, management and operations, evaluation, and application, while formalizing key definitions and introducing the design space. Our survey reveals that memory in LLM-MAS is not a trivial extension of single-agent memory but a distinct research frontier-with new challenges in synchronization, access control, scalability, alignment, and safety. By consolidating diverse literature, we aim to provide a foundation for future research in building intelligent, memory-augmented multi-agent systems. In order to follow the latest works in this field, we create and maintain a repository at https://github.com/ShanglinWu/LLM-MAS_Memory_Survey.git.

With the rapid advancement of large language models (LLMs), producing realistic fake news has become increasingly effortless, challenging existing detection methods that rely on lexical and syntactic patterns. To address this, we shift our focus to the generation process and analyze how malicious prompts manipulate model outputs. We construct pairs of LLM-generated real and fake news and apply malicious prompts to reconstruct them as fake. By comparing the original-token generation probabilities recorded during reconstruction, we observe a consistent statistical divergence: tokens from real news tend to have lower reconstruction likelihoods than those from fake news. We define this distributional divergence as linguistic fingerprint. Building on this insight, we propose LIFE (Linguistic Fingerprints Extraction), a novel detection framework that reconstructs token-level probability distributions guided by malicious prompts to capture these discriminative linguistic patterns. To fully exploit the extracted fingerprints, LIFE further introduces a key-fragment amplification module that adaptively identifies and accentuates the most distinctive linguistic fragments, thereby enhancing detection reliability across diverse prompting scenarios. Extensive experiments demonstrate that LIFE achieves state-of-the-art performance in detecting LLM-generated fake news while maintaining strong generalization to human-LLM mixed cases. The code is available.

Time series anomaly detection (TSAD) has been a long-standing pillar problem in Web-scale systems and online infrastructures, such as service reliability monitoring, system fault diagnosis, and performance optimization. Large language models (LLMs) have demonstrated unprecedented capabilities in time series analysis, the potential of multimodal LLMs (MLLMs), particularly vision-language models, in TSAD remains largely under-explored. One natural way for humans to detect time series anomalies is through visualization and textual description. It motivates our research question: Can multimodal LLMs perform time series anomaly detection? Existing studies often oversimplify the problem by treating point-wise anomalies as special cases of range-wise ones or by aggregating point anomalies to approximate range-wise scenarios. They limit our understanding for realistic scenarios such as multi-granular anomalies and irregular time series. To address the gap, we build a VisualTimeAnomaly benchmark to comprehensively investigate zero-shot capabilities of MLLMs for TSAD, progressively from point-, range-, to variate-wise anomalies, and extends to irregular sampling conditions. Our study reveals several key insights in multimodal MLLMs for TSAD. Built on these findings, we propose a MLLMs-based multi-agent framework TSAD-Agents to achieve automatic TSAD. Our framework comprises scanning, planning, detection, and checking agents that synergistically collaborate to reason, plan, and self-reflect to enable automatic TSAD. These agents adaptively invoke tools such as traditional methods and MLLMs and dynamically switch between text and image modalities to optimize detection performance.

The rapid proliferation of fake news on social media threatens social stability, creating an urgent demand for more effective detection methods. While many promising approaches have emerged, most rely on content analysis with limited semantic depth, leading to suboptimal comprehension of news content. To address this limitation, capturing broader-range semantics is essential yet challenging, as it introduces two primary types of noise: fully connecting sentences in news graphs often adds unnecessary structural noise, while highly similar but authenticity-irrelevant sentences introduce feature noise, complicating the detection process. To tackle these issues, we propose BREAK, a broad-range semantics model for fake news detection that leverages a fully connected graph to capture comprehensive semantics while employing dual denoising modules to minimize both structural and feature noise. The semantic structure denoising module balances the graph's connectivity by iteratively refining it between two bounds: a sequence-based structure as a lower bound and a fully connected graph as the upper bound. This refinement uncovers label-relevant semantic interrelations structures. Meanwhile, the semantic feature denoising module reduces noise from similar semantics by diversifying representations, aligning distinct outputs from the denoised graph and sequence encoders using KL-divergence to achieve feature diversification in high-dimensional space. The two modules are jointly optimized in a bi-level framework, enhancing the integration of denoised semantics into a comprehensive representation for detection. Extensive experiments across four datasets prove that BREAK significantly outperforms existing fake news detection methods.

Model attribution for LLM-generated disinformation poses a significant challenge in understanding its origins and mitigating its spread. This task is especially challenging because modern large language models (LLMs) produce disinformation with human-like quality. Additionally, the diversity in prompting methods used to generate disinformation complicates accurate source attribution. These methods introduce domain-specific features that can mask the fundamental characteristics of the models. In this paper, we introduce the concept of model attribution as a domain generalization problem, where each prompting method represents a unique domain. We argue that an effective attribution model must be invariant to these domain-specific features. It should also be proficient in identifying the originating models across all scenarios, reflecting real-world detection challenges. To address this, we introduce a novel approach based on Supervised Contrastive Learning. This method is designed to enhance the model's robustness to variations in prompts and focuses on distinguishing between different source LLMs. We evaluate our model through rigorous experiments involving three common prompting methods: “open-ended”, “rewriting”, and “paraphrasing”, and three advanced LLMs: “llama 2”, “chatgpt”, and “vicuna”. Our results demonstrate the effectiveness of our approach in model attribution tasks, achieving state-of-the-art performance across diverse and unseen datasets.

Graph anomaly detection has long been an important problem in various domains pertaining to information security such as financial fraud, social spam and network intrusion. The majority of existing methods are performed in an unsupervised manner, as labeled anomalies in a large scale are often too expensive to acquire. However, the identified anomalies may turn out to be uninteresting data instances due to the lack of prior knowledge. In real-world scenarios, it is often feasible to obtain limited labeled anomalies, which have great potential to advance graph anomaly detection. However, the work exploring limited labeled anomalies and a large amount of unlabeled nodes in graphs to detect anomalies is relatively limited. Therefore, in this paper, we study an important problem of few-shot graph anomaly detection. Nonetheless, it is challenging to fully leverage the information of few-shot anomalous nodes due to the irregularity of anomalies and the overfitting issue in the few-shot learning. To tackle the above challenges, we propose a novel meta-learning based framework, Meta-g Ad,that learns to adapt the knowledge from self-supervised learning to few-shot supervised learning for graph anomaly detection. In specific, we formulate the problem as a bi-level optimization, ensuring Metagad converging to minimizing the validation loss, thus enhancing the generalization capacity. The comprehensive experiments on six real-world datasets with synthetic anomalies and “organic” anomalies (available in the datasets) demonstrate the effectiveness of Metagad in detecting anomalies with few-shot anomalies. The code is available at https://github.com/XiongxiaoXu/MetaGAD.

Modern social media’s development has dramatically changed how people obtain information. However, the wide dissemination of various false information has severe detrimental effects. Accordingly, many deep learning-based methods have been proposed to detect false information and achieve promising results. However, these methods are unsuitable for new events due to the extremely limited labeled data and their discrepant data distribution to existing events. Domain adaptation methods have been proposed to mitigate these problems. However, their performance is suboptimal because they are not sensitive to new events due to they aim to align the domain information between existing events, and they hardly capture the fine-grained difference between real and fake claims by only using semantic information. Therefore, we propose a novel Emotion-aware Meta Learning (EML) approach for cross-event false information early detection, which deeply integrates emotions in meta learning to find event-sensitive initialization parameters that quickly adapt to new events. EML is non-trivial and faces three challenges: (1) How to effectively model semantic and emotional features to capture fine-grained differences? (2) How to reduce the impact of noise in meta learning based on semantic and emotional features? (3) How to detect the false information in a zero-shot detection scenario, i.e., no labeled data for new events? To tackle these challenges, firstly, we construct the emotion-aware meta tasks by selecting claims with similar and opposite emotions to the target claim other than usually used random sampling. Secondly, we propose a task weighting method and event-adaptation meta tasks to further improve the model’s robustness and generalization ability for detecting new events. Finally, we propose a weak label annotation method to extend EML to zero-shot detection according to the calculated labels’ confidence. Extensive experiments on real-world datasets show that the EML achieves superior performances on false information detection for new events.

Road safety is a major global public health concern, and effective prediction of traffic accidents at a fine-grained spatial scale plays a critical role in reducing roadway deaths and serious injuries. However, previous studies have either overlooked implicit spatial correlations or inadequately simulated road structures due to the lack of graph-structured datasets. To bridge this gap, we introduce a graph-based Traffic Accident Prediction (TAP) data repository, along with two representative tasks: accident occurrence and severity prediction. With its real-world graph structures, comprehensive geographical coverage, and rich geospatial features, this repository has considerable potential to facilitate various traffic-related tasks. We extensively evaluate eleven Graph Neural Network (GNN) baselines using the constructed datasets. We also develop a novel GNN-based model, which can capture additional angular and directional information from road networks. We demonstrate that the proposed model consistently outperforms the baselines. The data and code are available at https://github.com/baixianghuang/travel.

The ease of spreading false information online enables individuals with malicious intent to manipulate public opinion and destabilize social stability. Recently, fake news detection based on evidence retrieval has gained popularity in an effort to identify fake news reliably and reduce its impact. Evidence retrieval-based methods can improve the reliability of fake news detection by computing the textual consistency between the evidence and the claim in the news. In this paper, we propose a framework for fake news detection based on MUlti- Step Evidence Retrieval enhancement (MUSER), which simulates the steps of human beings in the process of reading news, summarizing, consulting materials, and inferring whether the news is true or fake. Our model can explicitly model dependencies among multiple pieces of evidence, and perform multi-step associations for the evidence required for news verification through multi-step retrieval. In addition, our model is able to automatically collect existing evidence through paragraph retrieval and key evidence selection, which can save the tedious process of manual evidence collection. We conducted extensive experiments on real-world datasets in different languages, and the results demonstrate that our proposed model outperforms state-of-the-art baseline methods for detecting fake news by at least 3% in F1-Macro and 4% in F1-Micro. Furthermore, it provides interpretable evidence for end users.

Social media is one of the main sources for news consumption, especially among the younger generation. With the increasing popularity of news consumption on various social media platforms, there has been a surge of misinformation which includes false information or unfounded claims. As various text- and social context-based fake news detectors are proposed to detect misinformation on social media, recent works start to focus on the vulnerabilities of fake news detectors. In this paper, we present the first adversarial attack framework against Graph Neural Network (GNN)-based fake news detectors to probe their robustness. Specifically, we leverage a multi-agent reinforcement learning (MARL) framework to simulate the adversarial behavior of fraudsters on social media. Research has shown that in real-world settings, fraudsters coordinate with each other to share different news in order to evade the detection of fake news detectors. Therefore, we modeled our MARL framework as a Markov Game with bot, cyborg, and crowd worker agents, which have their own distinctive cost, budget, and influence. We then use deep Q-learning to search for the optimal policy that maximizes the rewards. Extensive experimental results on two real-world fake news propagation datasets demonstrate that our proposed framework can effectively sabotage the GNN-based fake news detector performance. We hope this paper can provide insights for future research on fake news detection.

The wide spread of fake news is increasingly threatening both individuals and society. Great efforts have been made for automatic fake news detection on asingledomain (e.g., politics). However, correlations exist commonly across multiple news domains, and thus it is promising to simultaneously detect fake news ofmultipledomains. Based on our analysis, we pose two challenges in multi-domain fake news detection: 1)domain shift, caused by the discrepancy among domains in terms of words, emotions, styles, etc. 2)domain labeling incompleteness, stemming from the real-world categorization that only outputs one single domain label, regardless of topic diversity of a news piece. In this paper, we propose a Memory-guided Multi-view Multi-domain Fake News Detection Framework (M$^{3}$FEND) to address these two challenges. We model news pieces from a multi-view perspective, including semantics, emotion, and style. Specifically, we propose a Domain Memory Bank to enrich domain information which could discover potential domain labels based on seen news pieces and model domain characteristics. Then, with enriched domain information as input, a Domain Adapter could adaptively aggregate discriminative information from multiple views for news in various domains. Extensive offline experiments on English and Chinese datasets demonstrate the effectiveness of M$^{3}$FEND, and online tests verify its superiority in practice. Our code is available athttps://github.com/ICTMCG/M3FEND.

Nowadays, fake news easily propagates through online social networks and becomes a grand threat to individuals and society. Assessing the authenticity of news is challenging due to its elaborately fabricated contents, making it difficult to obtain large-scale annotations for fake news data. Due to such data scarcity issues, detecting fake news tends to fail and overfit in the supervised setting. Recently, graph neural networks (GNNs) have been adopted to leverage the richer relational information among both labeled and unlabeled instances. Despite their promising results, they are inherently focused on pairwise relations between news, which can limit the expressive power for capturing fake news that spreads in a group-level. For example, detecting fake news can be more effective when we better understand relations between news pieces shared among susceptible users. To address those issues, we propose to leverage a hypergraph to represent group-wise interaction among news, while focusing on important news relations with its dual-level attention mechanism. Experiments based on two benchmark datasets show that our approach yields remarkable performance and maintains the high performance even with a small subset of labeled news data.

Topic mining extracts patterns and insights from text data (e.g., documents, emails and product reviews), which can be used in various applications such as intent detection. However, topic mining can result in severe privacy threats to the users who have contributed to the text corpus since they can be re-identified from the text data with certain background knowledge. To our best knowledge, we propose the first differentially private topic mining technique (namely TopicDP) which injects well-calibrated Gaussian noise into the matrix output of any topic mining algorithm to ensure differential privacy and good utility. Specifically, we smoothen the sensitivity for the Gaussian mechanism via sensitivity sampling, which addresses the major challenges resulted from the high sensitivity in topic mining for differential privacy. Furthermore, we theoretically prove the differential privacy guarantee under the Rényi differential privacy mechanism and the utility error bounds of TopicDP. Finally, we conduct extensive experiments on two real-word text datasets (Enron email and Amazon Reviews), and the experimental results demonstrate that TopicDP is a model-agnostic framework that can generate better privacy preserving performance for topic mining as compared against other differential privacy mechanisms.

Despite the rapid development and great success of machine learning models, extensive studies have exposed their disadvantage of inheriting latent discrimination and societal bias from the training data. This phenomenon hinders their adoption on high-stake applications. Thus, many efforts have been taken for developing fair machine learning models. Most of them require that sensitive attributes are available during training to learn fair models. However, in many real-world applications, it is usually infeasible to obtain the sensitive attributes due to privacy or legal issues, which challenges existing fair-ensuring strategies. Though the sensitive attribute of each data sample is unknown, we observe that there are usually some non-sensitive features in the training data that are highly correlated with sensitive attributes, which can be used to alleviate the bias. Therefore, in this paper, we study a novel problem of exploring features that are highly correlated with sensitive attributes for learning fair and accurate classifiers. We theoretically show that by minimizing the correlation between these related features and model prediction, we can learn a fair classifier. Based on this motivation, we propose a novel framework which simultaneously uses these related features for accurate prediction and enforces fairness. In addition, the model can dynamically adjust the regularization weight of each related feature to balance its contribution on model classification and fairness. Experimental results on real-world datasets demonstrate the effectiveness of the proposed model for learning fair models with high classification accuracy.

With social media being a major force in information consumption, accelerated propagation of fake news has presented new challenges for platforms to distinguish between legitimate and fake news. Effective fake news detection is a non-trivial task due to the diverse nature of news domains and expensive annotation costs. In this work, we address the limitations of existing automated fake news detection models by incorporating auxiliary information (e.g., user comments and user-news interactions) into a novel reinforcement learning-based model called REinforced Adaptive Learning Fake News Detection (REAL-FND). REAL-FND exploits cross-domain and within-domain knowledge that makes it robust in a target domain, despite being trained in a different source domain. Extensive experiments on real-world datasets illustrate the effectiveness of the proposed model, especially when limited labeled data is available in the target domain.

Individuals can be misled by fake news and spread it unintentionally without knowing it is false. This phenomenon has been frequently observed but has not been investigated. Our aim in this work is to assess the intent of fake news spreaders. To distinguish between intentional versus unintentional spreading, we study the psychological explanations of unintentional spreading. With this foundation, we then propose an influence graph, using which we assess the intent of fake news spreaders. Our extensive experiments show that the assessed intent can help significantly differentiate between intentional and unintentional fake news spreaders. Furthermore, the estimated intent can significantly improve the current techniques that detect fake news. To our best knowledge, this is the first work to model individuals’ intent in fake news spreading.

Recently, the massive and diverse fake news from politics to entertainment and health has amplified the social distrust problem and has become a big challenge for the society and research community. The existing fake news detection methods are mostly designed for either a specific domain or require huge labeled data from various domains. If there is not enough labeled data in a certain domain, existing models may not work well for detecting fake news from that domain. To overcome these limitations we propose a novel framework based on multisource domain adaptation and weak supervision for early fake news detection. The framework transfers sufficient labeled source domains’ knowledge into a target/new domain with limited or even no labeled data by the multi-source domain adaptation, and applies researchers’ prior knowledge about fake news to the target domain by the weak supervision. The weak supervision assigns the weak labels to the unlabeled samples in the target domain through known heuristic rules. Our experimental results show that our approach outperforms 7 state-of-the-art methods in three real-world datasets. In particular, our model achieves, on average, 5.2% higher accuracy than the best baseline. Our model with a more advanced encoder can further boost the performance by 3.7%. The code is available at this clickable link.

The text generation methods have witnessed great success in text summarization, machine translation, and synthetic news generation. However, these techniques may be abused to generate disinformation and fake news. To better understand the potential threats of synthetic news, we develop a novel generation method RLTG to generate topic-preserving news content. The majority of existing text generation methods are either controlled by specific attributes or lack topic consistency between the input claims and output news, making synthetic news less coherent and realistic. In this paper, we study the problem of topic-preserving synthetic news generation by proposing a novel deep reinforcement learning-based method to control the output of large pre-trained language models. Experiment results on real-world datasets demonstrate that the news contents generated by RLTG are topic-consistent and realistic.

Recent years have witnessed remarkable progress towards computational fake news detection. To mitigate its negative impact, we argue that it is critical to understand what user attributes potentially cause users to share fake news. The key to this causal-inference problem is to identify confounders -- variables that cause spurious associations between treatments (e.g., user attributes) and outcome (e.g., user susceptibility). In fake news dissemination, confounders can be characterized by fake news sharing behavior that inherently relates to user attributes and online activities. Learning such user behavior is typically subject to selection bias in users who are susceptible to share news on social media. Drawing on causal inference theories, we first propose a principled approach to alleviating selection bias in fake news dissemination. We then consider the learned unbiased fake news sharing behavior as the surrogate confounder that can fully capture the causal links between user attributes and user susceptibility. We theoretically and empirically characterize the effectiveness of the proposed approach and find that it could be useful in protecting society from the perils of fake news.

The recent advanced deep learning techniques have shown the promising results in various domains such as computer vision and natural language processing. The success of deep neural networks in supervised learning heavily relies on a large amount of labeled data. However, obtaining labeled data with target labels is often challenging due to various reasons such as cost of labeling and privacy issues, which challenges existing deep models. In spite of that, it is relatively easy to obtain data with inexact supervision, i.e., having labels/tags related to the target task. For example, social media platforms are overwhelmed with billions of posts and images with self-customized tags, which are not the exact labels for target classification tasks but are usually related to the target labels. It is promising to leverage these tags (inexact supervision) and their relations with target classes to generate labeled data to facilitate the downstream classification tasks. However, the work on this is rather limited. Therefore, we study a novel problem of labeled data generation with inexact supervision. We propose a novel generative framework named as ADDES which can synthesize high-quality labeled data for target classification tasks by learning from data with inexact supervision and the relations between inexact supervision and target classes. Experimental results on image and text datasets demonstrate the effectiveness of the proposed ADDES for generating realistic labeled data from inexact supervision to facilitate the target classification task.

Misinformation and misbehavior mining on the web (MIS2) workshop is held virtually on August 14, 2021 and is co-located with the ACM SIGKDD 2021 conference. The web has become a breeding ground for misbehavior and misinformation. It is timely and crucial to understand, detect, forecast, and mitigate their harm. MIS2 workshop as an interdisciplinary venue for researchers and practitioners who study the dark side of the web. The workshop program includes a peer-reviewed set of paper presentations and keynote talks, giving the attendees an immersive experience of this research field.

Disinformation and fake news have posed detrimental effects on individuals and society in recent years, attracting broad attention to fake news detection. The majority of existing fake news detection algorithms focus on mining news content and/or the surrounding exogenous context for discovering deceptive signals; while the endogenous preference of a user when he/she decides to spread a piece of fake news or not is ignored. The confirmation bias theory has indicated that a user is more likely to spread a piece of fake news when it confirms his/her existing beliefs/preferences. Users' historical, social engagements such as posts provide rich information about users' preferences toward news and have great potentials to advance fake news detection. However, the work on exploring user preference for fake news detection is somewhat limited. Therefore, in this paper, we study the novel problem of exploiting user preference for fake news detection. We propose a new framework, UPFD, which simultaneously captures various signals from user preferences by joint content and graph modeling. Experimental results on real-world datasets demonstrate the effectiveness of the proposed framework. We release our code and data as a benchmark for GNN-based fake news detection: https://github.com/safe-graph/GNN-FakeNews.

Emotion plays an important role in detecting fake news online. When leveraging emotional signals, the existing methods focus on exploiting the emotions of news contents that conveyed by the publishers (i.e., publisher emotion). However, fake news often evokes high-arousal or activating emotions of people, so the emotions of news comments aroused in the crowd (i.e., social emotion) should not be ignored. Furthermore, it remains to be explored whether there exists a relationship between publisher emotion and social emotion (i.e., dual emotion), and how the dual emotion appears in fake news. In this paper, we verify that dual emotion is distinctive between fake and real news and propose Dual Emotion Features to represent dual emotion and the relationship between them for fake news detection. Further, we exhibit that our proposed features can be easily plugged into existing fake news detectors as an enhancement. Extensive experiments on three real-world datasets (one in English and the others in Chinese) show that our proposed feature set: 1) outperforms the state-of-the-art task-related emotional features; 2) can be well compatible with existing fake news detectors and effectively improve the performance of detecting fake news.1 2

The COVID-19 epidemic is considered as the global health crisis of the whole society and the greatest challenge mankind faced since World War Two. Unfortunately, the fake news about COVID-19 is spreading as fast as the virus itself. The incorrect health measurements, anxiety, and hate speeches will have bad consequences on people's physical health, as well as their mental health in the whole world. To help better combat the COVID-19 fake news, we propose a new fake news detection dataset MM-COVID1(Multilingual and Multidimensional COVID-19 Fake News Data Repository). This dataset provides the multilingual fake news and the relevant social context. We collect 3981 pieces of fake news content and 7192 trustworthy information from English, Spanish, Portuguese, Hindi, French and Italian, 6 different languages. We present a detailed and exploratory analysis of MM-COVID from different perspectives.

For the fifth edition of the workshop on Mining Actionable Insights from Social Networks (MAISoN), we organized a special edition with focus on dis/misinformation mining from social media, co-located with CIKM 2020. This topic has attracted a lot of interest from the community since the Coronavirus (COVID-19) epidemic has given rise to an increase of misinformation on social media. The aim of this edition was to bring together researchers from different disciplines interested in mining dis/misinformation on social media. In particular, the distinguishing focus of this special edition was its emphasis on techniques that use social media data for building diagnostic, predictive and prescriptive analysis models related to misinformation. This means that there is rigorous attention for techniques that can be used to understand how and why dis/misinformation is created and spread, to uncover hidden and unexpected aspects of dis/misinformation content, and to recommend insightful countermeasures to restrict the circulation of dis/misinformation and alleviate their negative effects.

Social media is a vital means for information-sharing due to its easy access, low cost, and fast dissemination characteristics. However, increases in social media usage have corresponded with a rise in the prevalence of cyberbullying. Most existing cyberbullying detection methods aresupervised and, thus, have two key drawbacks: (1) The data labeling process is often time-consuming and labor-intensive; (2) Current labeling guidelines may not be generalized to future instances because of different language usage and evolving social networks. To address these limitations, this work introduces a principled approach forunsupervised cyberbullying detection. The proposed model consists of two main components: (1) Arepresentation learning network that encodes the social media session by exploiting multi-modal features, e.g., text, network, and time. (2) Amulti-task learning network that simultaneously fits the comment inter-arrival times and estimates the bullying likelihood based on a Gaussian Mixture Model. The proposed model jointly optimizes the parameters of both components to overcome the shortcomings of decoupled training. Our core contribution is an unsupervised cyberbullying detection model that not only experimentally outperforms the state-of-the-art unsupervised models, but also achieves competitive performance compared to supervised models.

Attributed networks nowadays are ubiquitous in a myriad of high-impact applications, such as social network analysis, financial fraud detection, and drug discovery. As a central analytical task on attributed networks, node classification has received much attention in the research community. In real-world attributed networks, a large portion of node classes only contains limited labeled instances, rendering a long-tail node class distribution. Existing node classification algorithms are unequipped to handle the few-shot node classes. As a remedy, few-shot learning has attracted a surge of attention in the research community. Yet, few-shot node classification remains a challenging problem as we need to address the following questions: (i) How to extract meta-knowledge from an attributed network for few-shot node classification? (ii) How to identify the informativeness of each labeled instance for building a robust and effective model? To answer these questions, in this paper, we propose a graph meta-learning framework -- Graph Prototypical Networks (GPN). By constructing a pool of semi-supervised node classification tasks to mimic the real test environment, GPN is able to perform meta-learning on an attributed network and derive a highly generalizable model for handling the target classification task. Extensive experiments demonstrate the superior capability of GPN in few-shot node classification.

Email remains one of the most frequently used means of online communication. People spend significant amount of time every day on emails to exchange information, manage tasks and schedule events. Previous work has studied different ways for improving email productivity by prioritizing emails, suggesting automatic replies or identifying intents to recommend appropriate actions. The problem has been mostly posed as a supervised learning problem where models of different complexities were proposed to classify an email message into a predefined taxonomy of intents or classes. The need for labeled data has always been one of the largest bottlenecks in training supervised models. This is especially the case for many real-world tasks, such as email intent classification, where large scale annotated examples are either hard to acquire or unavailable due to privacy or data access constraints. Email users often take actions in response to intents expressed in an email (e.g., setting up a meeting in response to an email with a scheduling request). Such actions can be inferred from user interaction logs. In this paper, we propose to leverage user actions as a source of weak supervision, in addition to a limited set of annotated examples, to detect intents in emails. We develop an end-to-end robust deep neural network model for email intent identification that leverages both clean annotated data and noisy weak supervision along with a self-paced learning mechanism. Extensive experiments on three different intent detection tasks show that our approach can effectively leverage the weakly supervised data to improve intent detection in emails.

The correlation network, typically formed by computing pairwise correlations between variables, has recently become a competitive paradigm to discover insights in various application domains, such as climate prediction, financial marketing, and bioinformatics. In this study, we adopt this paradigm to detect cheating behavior hidden in business distribution channels, where falsified big deals are often made by collusive partners to obtain lower product prices—a behavior deemed to be extremely harmful to the sale ecosystem. To this end, we assume that abnormal deals are likely to occur between two partners if their purchase-volume sequences have a strong negative correlation. This seemingly intuitive rule, however, imposes several research challenges. First, existing correlation measures are usually symmetric and thus cannot distinguish the different roles of partners in cheating. Second, the tick-to-tick correspondence between two sequences might be violated due to the possible delay of purchase behavior, which should also be captured by correlation measures. Finally, the fact that any pair of sequences could be correlated may result in a number of false-positive cheating pairs, which need to be corrected in a systematic manner. To address these issues, we propose a correlation network analysis framework for cheating detection. In the framework, we adopt an asymmetric correlation measure to distinguish the two roles, namely, cheating seller and cheating buyer , in a cheating alliance. Dynamic Time Warping is employed to address the time offset between two sequences in computing the correlation. We further propose two graph-cut methods to convert the correlation network into a bipartite graph to rank cheating partners, which simultaneously helps to remove false-positive correlation pairs. Based on a 4-year real-world channel dataset from a worldwide IT company, we demonstrate the effectiveness of the proposed method in comparison to competitive baseline methods.

Clickbait is an attractive yet misleading headline that lures readers to commit click-conversion. Development of robust clickbait detection models has been, however, hampered due to the shortage of high-quality labeled training samples. To overcome this challenge, we investigate how to exploit human-written and machine-generated synthetic clickbaits. We first ask crowdworkers and journalism students to generate clickbaity news headlines. Second, we utilize deep generative models to generate clickbaity headlines. Through empirical evaluations, we demonstrate that synthetic clickbaits by human entities and deep generative models are consistently useful in improving the accuracy of various prediction models, by as much as 14.5% in AUC, across two real datasets and different types of algorithms. Especially, we observe an improvement in accuracy, up to 8.5% in AUC, even for top-ranked clickbait detectors from Clickbait Challenge 2017. Our study proposes a novel direction to address the shortage of labeled training data, one of fundamental bottlenecks in supervised learning, by means of synthetic training data with reinforced domain knowledge. It also provides a solution for distinguishing between bot-generated and human-written clickbaits, thus aiding the work of moderators and better alerting news consumers.

Consuming news from social media is becoming increasingly popular. Social media appeals to users due to its fast dissemination of information, low cost, and easy access. However, social media also enables the widespread of fake news. Due to the detrimental societal effects of fake news, detecting fake news has attracted increasing attention. However, the detection performance only using news contents is generally not satisfactory as fake news is written to mimic true news. Thus, there is a need for an in-depth understanding on the relationship between user profiles on social media and fake news. In this paper, we study the problem of understanding and exploiting user profiles on social media for fake news detection. In an attempt to understand connections between user profiles and fake news, first, we measure users' sharing behaviors and group representative users who are more likely to share fake and real news; then, we perform a comparative analysis of explicit and implicit profile features between these user groups, which reveals their potential to help differentiate fake news from real news. To exploit user profile features, we demonstrate the usefulness of these user profile features in a fake news classification task. We further validate the effectiveness of these features through feature importance analysis. The findings of this work lay the foundation for deeper exploration of user profile features of social media and enhance the capabilities for fake news detection.

Despite recent advancements in computationally detecting fake news, we argue that a critical missing piece be the explainability of such detection--i.e., why a particular piece of news is detected as fake--and propose to exploit rich information in users' comments on social media to infer the authenticity of news. In this demo paper, we present our system for an explainable fake news detection called dEFEND, which can detect the authenticity of a piece of news while identifying user comments that can explain why the news is fake or real. Our solution develops a sentence-comment co-attention sub-network to exploit both news contents and user comments to jointly capture explainable top-k check-worthy sentences and user comments for fake news detection. The system is publicly accessible.

In recent years, to mitigate the problem of fake news, computational detection of fake news has been studied, producing some promising early results. While important, however, we argue that a critical missing piece of the study be the explainability of such detection, i.e., why a particular piece of news is detected as fake. In this paper, therefore, we study the explainable detection of fake news. We develop a sentence-comment co-attention sub-network to exploit both news contents and user comments to jointly capture explainable top-k check-worthy sentences and user comments for fake news detection. We conduct extensive experiments on real-world datasets and demonstrate that the proposed method not only significantly outperforms 7 state-of-the-art fake news detection methods by at least 5.33% in F1-score, but also (concurrently) identifies top-k user comments that explain why a news piece is fake, better than baselines by 28.2% in NDCG and 30.7% in Precision.

Fake news has become a global phenomenon due its explosive growth, particularly on social media. The goal of this tutorial is to (1) clearly introduce the concept and characteristics of fake news and how it can be formally differentiated from other similar concepts such as mis-/dis-information, satire news, rumors, among others, which helps deepen the understanding of fake news; (2) provide a comprehensive review of fundamental theories across disciplines and illustrate how they can be used to conduct interdisciplinary fake news research, facilitating a concerted effort of experts in computer and information science, political science, journalism, social science, psychology and economics. Such concerted efforts can result in highly efficient and explainable fake news detection; (3) systematically present fake news detection strategies from four perspectives (i.e., knowledge, style, propagation, and credibility) and the ways that each perspective utilizes techniques developed in data/graph mining, machine learning, natural language processing, and information retrieval; and (4) detail open issues within current fake news studies to reveal great potential research opportunities, hoping to attract researchers within a broader area to work on fake news detection and further facilitate its development. The tutorial aims to promote a fair, healthy and safe online information and news dissemination ecosystem, hoping to attract more researchers, engineers and students with various interests to fake news research. Few prerequisite are required for KDD participants to attend.

Recommendation in the modern world is not only about capturing the interaction between users and items, but also about understanding the relationship between items. Besides improving the quality of recommendation, it enables the generation of candidate items that can serve as substitutes and supplements of another item. For example, when recommending Xbox, PS4 could be a logical substitute and the supplements could be items such as game controllers, surround system, and travel case. Therefore, given a network of items, our objective is to learn their content features such that they explain the relationship between items in terms of substitutes and supplements. To achieve this, we propose a generative deep learning model that links two variational autoencoders using a connector neural network to create Linked Variational Autoencoder (LVA). LVA learns the latent features of items by conditioning on the observed relationship between items. Using a rigorous series of experiments, we show that LVA significantly outperforms other representative and state-of-the-art baseline methods in terms of prediction accuracy. We then extend LVA by incorporating collaborative filtering (CF) to create CLVA that captures the implicit relationship between users and items. By comparing CLVA with LVA we show that inducing CF-based features greatly improve the recommendation quality of substitutable and supplementary items on a user level.

Social media is becoming popular for news consumption due to its fast dissemination, easy access, and low cost. However, it also enables the wide propagation of fake news, i.e., news with intentionally false information. Detecting fake news is an important task, which not only ensures users receive authentic information but also helps maintain a trustworthy news ecosystem. The majority of existing detection algorithms focus on finding clues from news contents, which are generally not effective because fake news is often intentionally written to mislead users by mimicking true news. Therefore, we need to explore auxiliary information to improve detection. The social context during news dissemination process on social media forms the inherent tri-relationship, the relationship among publishers, news pieces, and users, which has the potential to improve fake news detection. For example, partisan-biased publishers are more likely to publish fake news, and low-credible users are more likely to share fake news. In this paper, we study the novel problem of exploiting social context for fake news detection. We propose a tri-relationship embedding framework TriFN, which models publisher-news relations and user-news interactions simultaneously for fake news classification. We conduct experiments on two real-world datasets, which demonstrate that the proposed approach significantly outperforms other baseline methods for fake news detection.

The explosive growth of fake news and its erosion to democracy, justice, and public trust increased the demand for fake news detection. As an interdisciplinary topic, the study of fake news encourages a concerted effort of experts in computer and information science, political science, journalism, social science, psychology, and economics. A comprehensive framework to systematically understand and detect fake news is necessary to attract and unite researchers in related areas to conduct research on fake news. This tutorial aims to clearly present (1) fake news research, its challenges, and research directions; (2) a comparison between fake news and other related concepts (e.g., rumors); (3) the fundamental theories developed across various disciplines that facilitate interdisciplinary research; (4) various detection strategies unified under a comprehensive framework for fake news detection; and (5) the state-of-the-art datasets, patterns, and models. We present fake news detection from various perspectives, which involve news content and information in social networks, and broadly adopt techniques in data mining, machine learning, natural language processing, information retrieval and social search. Facing the upcoming 2020 U.S. presidential election, challenges for automatic, effective and efficient fake news detection are also clarified in this tutorial.

Mobile Applications (or Apps) are becoming more and more popular in recent years, which has attracted increasing attention on mobile App recommendations. The majority of existing App recommendation algorithms focus on mining App functionality or user usage data for discovering user preferences; while actions taken by a user when he/she decides to download an App or not are ignored. In realistic scenarios, a user will first view the description of the App and then decide if he/she wants to download it or not. The actions such as viewing or downloading provide rich information about users' preferences and tastes for Apps, which have great potentials to advance App recommendations. However, the work on exploring action data for App recommendations is rather limited. Therefore, in this paper we study the novel problem of exploiting user actions for App recommendations. We propose a new framework ActionRank, which simultaneously captures various signals from user actions for App recommendations. Experimental results on real-world datasets demonstrate the effectiveness of the proposed framework.

Clickbaits are catchy social posts or sensational headlines that attempt to lure readers to click. Clickbaits are pervasive on social media and can have significant negative impacts on both users and media ecosystems. For example, users may be misled to receive inaccurate information or fall into click-jacking attacks. Similarly, media platforms could lose readers' trust and revenues due to the prevalence of clickbaits. To computationally detect such clickbaits on social media using a supervised learning framework, one of the major obstacles is the lack of large-scale labeled training data, due to the high cost of labeling. With the recent advancements of deep generative models, to address this challenge, we propose to generate synthetic headlines with specific styles and explore their utilities to help improve clickbait detection. In particular, we propose to generate stylized headlines from original documents with style transfer. Furthermore, as it is non-trivial to generate stylized headlines due to several challenges such as the discrete nature of texts and the requirements of preserving semantic meaning of document while achieving style transfer, we propose a novel solution, named as Stylized Headline Generation (SHG), that can not only generate readable and realistic headlines to enlarge original training data, but also help improve the classification capacity of supervised learning. The experimental results on real-world datasets demonstrate the effectiveness of SHG in generating high-quality and high-utility headlines for clickbait detection.

Friend and item recommendation on a social media site is an important task, which not only brings conveniences to users but also benefits platform providers. However, recommendation for newly launched social media sites is challenging because they often lack user historical data and encounter data sparsity and cold-start problem. Thus, it is important to exploit auxiliary information to help improve recommendation performances on these sites. Existing approaches try to utilize the knowledge transferred from other mature sites, which often require overlapped users or similar items to ensure an effective knowledge transfer. However, these assumptions may not hold in practice because 1) Overlapped user set is often unavailable and costly to identify due to the heterogeneous user profile, content and network data, and 2) Different schemes to show item attributes across sites cause the attribute values inconsistent, incomplete, and noisy. Thus, how to transfer knowledge when no direct bridge is given between two social media sites remains a challenge. In addition, another auxiliary information we can exploit is the mutual benefit between social relationships and rating preferences within the platform. User-user relationships are widely used as side information to improve item recommendation, whereas how to exploit user-item interactions for friend recommendation is rather limited. To tackle these challenges, we propose aCross media jointF riend andI temRe commendation framework (CrossFire ), which can capture both 1) cross-platform knowledge transfer, and 2) within-platform correlations among user-user relations and user-item interactions. Empirical results on real-world datasets demonstrate the effectiveness of the proposed framework.

The rapid growth of Location-based Social Networks (LBSNs) provides a vast amount of check-in data, which facilitates the study of point-of-interest (POI) recommendation. The majority of the existing POI recommendation methods focus on four aspects, i.e., temporal patterns, geographical influence, social correlations and textual content indications. For example, user's visits to locations have temporal patterns and users are likely to visit POIs near them. In real-world LBSNs such as Instagram, users can upload photos associating with locations. Photos not only reflect users' interests but also provide informative descriptions about locations. For example, a user who posts many architecture photos is more likely to visit famous landmarks; while a user posts lots of images about food has more incentive to visit restaurants. Thus, images have potentials to improve the performance of POI recommendation. However, little work exists for POI recommendation by exploiting images. In this paper, we study the problem of enhancing POI recommendation with visual contents. In particular, we propose a new framework Visual Content Enhanced POI recommendation (VPOI), which incorporates visual contents for POI recommendations. Experimental results on real-world datasets demonstrate the effectiveness of the proposed framework.

Distribution channel is a system that partners move products from manufacturer to end users. To increase sales, it is quite common for manufacturers to adjust the product prices to partners according to the product volume per deal. However, the price adjustment is like a double-edged sword. It also spurs some partners to form a cheating alliance, where a cheating seller applies for a falsified big deal with a low price and then re-sells the products to the cheating buyers. Since these cheating behaviors are harmful to a healthy ecosystem of distribution channel, we need the automatic method to guide the tedious audit process.