Multi-modal dataset distillation (DD) condenses large datasets into compact ones that retain task efficacy by capturing correspondence patterns, i.e., shared semantics between paired modalities. However, such patterns rely on cross-modal similarity and cannot be faithfully captured by intra-modal similarity of current unimodal strategies. As a result, current multi-modal DD methods tend to over-concentrate, redundantly encoding similar correspondence patterns and thus limiting generalizability. To this end, we propose a novel multi-modal DD framework to systematically Promote Correspondence coverage, i.e., ProCo. Initially, we develop a correspondence consistency metric based on cross-modal retrieval distributions to cluster correspondence patterns. These clusters capture the underlying correspondence distribution, enabling ProCo to initialize distilled data with representative patterns while regularizing optimization to promote correspondence representativeness and diversity. Moreover, we employ conditional neural fields for efficient distilled data parameterization, enhancing fine-grained pattern capture while allowing more distilled data under a fixed budget to boost correspondence coverage. Extensive experiments verify that our ProCo achieves superior and elastic budget-efficacy trade-offs, surpassing prior methods by over 15% with 10x distillation budget reduction, highlighting its real-world practicality.

While existing social bot detectors perform well on benchmarks, their robustness across diverse real-world scenarios remains limited due to unclear ground truth and varied misleading cues. In particular, the impact of shortcut learning, where models rely on spurious correlations instead of capturing causal task-relevant features, has received limited attention. To address this gap, we conduct an in-depth study to assess how detectors are influenced by potential shortcuts based on textual features, which are most susceptible to manipulation by social bots. We design a series of shortcut scenarios by constructing spurious associations between user labels and superficial textual cues to evaluate model robustness. Results show that shifts in irrelevant feature distributions significantly degrade social bot detector performance, with an average relative accuracy drop of 32 % in the baseline models. To tackle this challenge, we propose mitigation strategies based on large language models, leveraging counterfactual data augmentation. These methods mitigate the problem from data and model perspectives across three levels, including data distribution at both the individual user text and overall dataset levels, as well as model’s ability to extract causal information. Our strategies achieve an average relative performance improvement of 56 % under shortcut scenarios.

Zhi Zeng, Jiaying Wu, Minnan Luo, Di Zhang, Yifei Yang, Xiangzheng Kong, Herun Wan, Zihan Ma. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

The rise of micro-videos has reshaped how misinformation spreads, amplifying its speed, reach, and impact on public trust. Existing benchmarks typically focus on a single deception type, overlooking the diversity of real-world cases that involve multimodal manipulation, AI-generated content, cognitive bias, and out-of-context reuse. Meanwhile, most detection models lack fine-grained attribution, limiting interpretability and practical utility. To address these gaps, we introduce WildFakeBench, a large-scale benchmark of over 10,000 real-world micro-videos covering diverse misinformation types and sources, each annotated with expert-defined attribution labels. Building on this foundation, we develop FakeAgent, a Delphi-inspired multi-agent reasoning framework that integrates multimodal understanding with external evidence for attribution-grounded analysis. FakeAgent jointly analyzes content and retrieved evidence to identify manipulation, recognize cognitive and AI-generated patterns, and detect out-of-context misinformation. Extensive experiments show that FakeAgent consistently outperforms existing MLLMs across all misinformation types, while WildFakeBench provides a realistic and challenging testbed for advancing explainable micro-video misinformation detection. Data and code are available at: https://github.com/Aiyistan/FakeAgent.

These years have witnessed remarkable progress in modeling user behaviour from personalized online services, especially knowledge graph-based recommendation systems. Meanwhile, more studies are focusing on aspects beyond recommendation performance, since such an observational data-driven paradigm is posing threats to both users and society in terms of trustworthiness. In fact, existing problem-oriented solutions still face significant challenges, as almost all of them suffer from the generality limitations to improve their trustworthiness in a uniform fashion. To address these issues, we propose a plug-and-playDebiasing framework forKnowledgeGraph-basedRecommendationSystems, also known as DiKGRS. Specifically, the Knowledge-augmented Pseudo-Samples Generation (KPSG) method, a novel data augmentation perspective, is proposed to explore more auxiliary information beyond observational user behaviors. Furthermore, the Debiasing Value Networks (DVN), is also developed to evaluate the reliability of generated pseudo-samples by modeling both the item popularity and user demographic bias in the platform. Moreover, an adaptive weighting coordination module is performed to coordinate the proposed DiKGRS framework and its backbones. Experimental results on four real-world datasets from different online service personalization scenarios have illustrated that the proposed framework can significantly improve the trustworthiness of existing knowledge graph-based recommendation systems. The code has been released public available at:https://github.com/alipay/A-Knowledge-augmented-Method-DiKGRS.

Social platforms, while facilitating access to information, have also become saturated with a plethora of fake news, resulting in negative consequences. Automatic multimodal fake news detection is a worthwhile pursuit. Existing multimodal fake news datasets only provide binary labels of real or fake. However, real news is alike, while each fake news is fake in its own way. These datasets fail to reflect the mixed nature of various types of multimodal fake news. To bridge the gap, we construct an attributing multi-granularity multimodal fake news detection dataset AMG, revealing the inherent fake pattern. Furthermore, we propose a multi-granularity clue alignment model MGCA to achieve multimodal fake news detection and attribution. Experimental results demonstrate that AMG is a challenging dataset, and its attribution setting opens up new avenues for future research.

The misuse of large language models (LLMs) poses potential risks, motivating the development of machine-generated text (MGT) detection. Existing literature primarily concentrates on binary, document-level detection, thereby neglecting texts that are composed jointly by human and LLM contributions. Hence, this paper explores the possibility of fine-grained MGT detection under human-AI coauthoring.We suggest fine-grained detectors can pave pathways toward coauthored text detection with a numeric AI ratio.Specifically, we propose a dataset, HACo-Det, which produces human-AI coauthored texts via an automatic pipeline with word-level attribution labels. We retrofit seven prevailing document-level detectors to generalize them to word-level detection.Then we evaluate these detectors on HACo-Det on both word- and sentence-level detection tasks.Empirical results show that metric-based methods struggle to conduct fine-grained detection with a 0.462 average F1 score, while finetuned models show superior performance and better generalization across domains. However, we argue that fine-grained co-authored text detection is far from solved.We further analyze factors influencing performance, e.g., context window, and highlight the limitations of current methods, pointing to potential avenues for improvement.

Evidence-enhanced detectors present remarkable abilities in identifying malicious social text.However, the rise of large language models (LLMs) brings potential risks of evidence pollution to confuse detectors.This paper explores potential manipulation scenarios including basic pollution, and rephrasing or generating evidence by LLMs.To mitigate the negative impact, we propose three defense strategies from the data and model sides, including machine-generated text detection, a mixture of experts, and parameter updating.Extensive experiments on four malicious social text detection tasks with ten datasets illustrate that evidence pollution significantly compromises detectors, where the generating strategy causes up to a 14.4% performance drop.Meanwhile, the defense strategies could mitigate evidence pollution, but they faced limitations for practical employment.Further analysis illustrates that polluted evidence (i) is of high quality, evaluated by metrics and humans; (ii) would compromise the model calibration, increasing expected calibration error up to 21.6%; and (iii) could be integrated to amplify the negative impact, especially for encoder-based LMs, where the accuracy drops by 21.8%.

Zhi Zeng, Jiaying Wu, Minnan Luo, Herun Wan, Xiangzheng Kong, Zihan Ma, Guang Dai, Qinghua Zheng. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

In the era of social media, the proliferation of fake news has created an urgent need for more effective detection methods, particularly for multimodal content. The task of identifying fake news is highly challenging, as it requires broad background knowledge and understanding across various domains. Existing detection methods primarily rely on neural networks to learn latent feature representations, resulting in black-box classifications with limited real-world understanding. To address these limitations, we propose a novel approach that leverages Multimodal Large Language Models (MLLMs) for fake news detection. Our method introduces adversarial reasoning through debates from opposing perspectives. By harnessing the powerful capabilities of MLLMs in text generation and cross-modal reasoning, we guide these models to engage in multimodal debates, generating adversarial arguments based on contradictory evidence from both sides of the issue. We then utilize these arguments to learn reasonable thinking patterns, enabling better multimodal fusion and fine-tuning. This process effectively positions our model as a debate referee for adversarial inference. Extensive experiments conducted on four fake news detection datasets demonstrate that our proposed method significantly outperforms state-of-the-art approaches.

Despite the significant advancements in text-to-image (T2I) generative models, users often face a trial-and-error challenge in practical scenarios. This challenge arises from the complexity and uncertainty of tedious steps such as crafting suitable prompts, selecting appropriate models, and configuring specific arguments, making users resort to labor-intensive attempts for desired images. This paper proposes Automatic T2I generation, which aims to automate these tedious steps, allowing users to simply describe their needs in a freestyle chatting way. To systematically study this problem, we first introduce ChatGenBench, a novel benchmark designed for Automatic T2I. It features high-quality paired data with diverse freestyle inputs, enabling comprehensive evaluation of automatic T2I models across all steps. Additionally, recognizing Automatic T2I as a complex multi-step reasoning task, we propose ChatGen-Evo, a multi-stage evolution strategy that progressively equips models with essential automation skills. Through extensive evaluation across step-wise accuracy and image quality, ChatGen-Evo significantly enhances performance over various baselines. Our evaluation also uncovers valuable insights for advancing automatic T2I. Our data, code, and models will be publicly available.

Social media platforms provide an ideal environment to spread misinformation, where social bots can accelerate the spread.This paper explores the interplay between social bots and misinformation on the Sina Weibo platform.We construct a large-scale dataset that includes annotations for both misinformation and social bots.From the misinformation perspective, the dataset is multimodal, containing 11,393 pieces of misinformation and 16,416 pieces of verified information.From the social bot perspective, this dataset contains 65,749 social bots and 345,886 genuine accounts, annotated using a weakly supervised annotator.Extensive experiments demonstrate the comprehensiveness of the dataset, the clear distinction between misinformation and real information, and the high quality of social bot annotations.Further analysis illustrates that: (i) social bots are deeply involved in information spread; (ii) misinformation with the same topics has similar content, providing the basis of echo chambers, and social bots would amplify this phenomenon; and (iii) social bots generate similar content aiming to manipulate public opinions.

In Large Language Models (LLMs) generation, there exist knowledge conflicts and scenarios where parametric knowledge contradicts knowledge provided in the context.Previous works studied tuning, decoding algorithms, or locating and editing context-aware neurons to adapt LLMs to be faithful to new contextual knowledge.However, they are usually inefficient or ineffective for large models, not workable for black-box models, or unable to continuously adjust LLMs' sensitivity to the knowledge provided in the context.To mitigate these problems, we propose CSKS (Continuously Steering Knowledge Sensitivity), a simple framework that can steer LLMs' sensitivity to contextual knowledge continuously at a lightweight cost.Specifically, we tune two small LMs (i.e.proxy models) and use the difference in their output distributions to shift the original distribution of an LLM without modifying the LLM weights.In the evaluation process, we not only design synthetic data and fine-grained metrics to measure models' sensitivity to contextual knowledge but also use a real conflict dataset to validate CSKS's practical efficacy.Extensive experiments demonstrate that our framework achieves continuous and precise control over LLMs' sensitivity to contextual knowledge, enabling both increased sensitivity and reduced sensitivity, thereby allowing LLMs to prioritize either contextual or parametric knowledge as needed flexibly.Our data and code are available at https: //github.com/OliveJuiceLin/CSKS.

Short videos have become a pivotal medium for news dissemination but have also accelerated the spread of fake news. Although existing detection methods have achieved significant results, they often neglect the impact of noise in multimodal data, resulting in degraded detection accuracy and limited generalization. To address these challenges, we propose the Progressive Noise-Resilient Network (PNRN), a framework designed to adaptively mitigate noise in complex scenarios. PNRN comprises two key components: a unimodal noise-resilient module and a multimodal adaptive fusion module. The unimodal noise-resistant module leverages information bottlenecks to effectively filter modality-specific noise and strengthen feature relevance within individual modalities. The multimodal adaptive fusion module employs dynamic multi-routing and a mixture of experts to dynamically prioritize informative multimodal representations while reducing cross-modal inconsistencies. Experimental results demonstrate that PNRN significantly enhances fake news video detection performance and exhibits strong generalization capabilities in diverse and noisy social environments. Main code is available at https://anonymous.4open.science/r/PNRN-F308.

As short videos become a dominant medium for news dissemination, fake news videos pose increasing threats to public trust and information integrity. Existing methods primarily focus on learning multimodal representations to predict binary veracity labels, yet they overlook the use of external evidence, which is important for identifying more sophisticated fake news that subtly exploits psychological cues and cognitive biases. Moreover, these approaches do not provide fine-grained attribution labels, which are essential for interpretable misinformation governance. To address these limitations, we introduce EvidSV, the first comprehensive benchmark supporting evidence- and attribution-aware fake news video detection. Drawing inspiration from the human cognitive process of interpreting news-related content, we propose MUKE, a multi-view knowledge progressive enhancement learning framework. By jointly analyzing both the news content and supporting evidence, MUKE (1) facilitates the understanding of news semantics to (2) progressively refine shared domain knowledge, and (3) adaptively summarizes multi-view knowledge to assess news veracity. Extensive experiments demonstrate that MUKE consistently outperforms existing methods in both fake news detection and attribution, and generalizes effectively to previously unseen domains. Our code is available at https://github.com/zzeng1998/EvidSV.

Large language models (LLMs) have recently achieved notable success in code‑generation benchmarks such as HumanEval and LiveCodeBench. However, a detailed examination reveals that these evaluation suites often comprise only a limited number of homogeneous test cases, resulting in subtle faults going undetected. This not only artificially inflates measured performance but also compromises accurate reward estimation in reinforcement learning frameworks utilizing verifiable rewards (RLVR). To address these critical shortcomings, we systematically investigate the test-case generation (TCG) task by proposing multi-dimensional metrics designed to rigorously quantify test-suite thoroughness. Furthermore, we introduce a human-LLM collaborative method (SAGA), leveraging human programming expertise with LLM reasoning capability, aimed at significantly enhancing both the coverage and the quality of generated test cases. In addition, we develop a TCGBench to facilitate the study of the TCG task. Experiments show that SAGA achieves a detection rate of 90.62\% and a verifier accuracy of 32.58\% on TCGBench. The Verifier Accuracy (Verifier Acc) of the code generation evaluation benchmark synthesized by SAGA is 10.78\% higher than that of LiveCodeBench-v6. These results demonstrate the effectiveness of our proposed method. We hope this work contributes to building a scalable foundation for reliable LLM code evaluation, further advancing RLVR in code generation, and paving the way for automated adversarial test synthesis and adaptive benchmark integration.

Misinformation detectors often rely on superficial cues (i.e., shortcuts) that correlate with misinformation in training data but fail to generalize to the diverse and evolving nature of real-world misinformation. This issue is exacerbated by large language models (LLMs), which can easily generate convincing misinformation using simple prompts. We introduce TruthOverTricks, a unified evaluation paradigm for measuring shortcut learning in misinformation detection. TruthOverTricks categorizes shortcut behaviors into intrinsic shortcut induction and extrinsic shortcut injection, and evaluates seven representative detectors across 14 popular benchmarks, along with two new factual misinformation datasets, NQ-Misinfo and Streaming-Misinfo. Empirical results reveal that existing detectors suffer severe performance degradation when exposed to both naturally occurring and adversarially crafted shortcuts. To address this, we propose the Shortcut Mitigation Framework (SMF), an LLM-augmented data augmentation framework that mitigates shortcut reliance through paraphrasing, factual summarization, and sentiment normalization. SMF consistently enhances robustness across 16 benchmarks, forcing models to rely on deeper semantic understanding rather than shortcut cues.

While the proliferation of fake news poses a significant threat to information integrity, existing efforts to counter it, especially within personalized news recommendation systems, have proven inadequate.Traditional methods, which often rely on classifiers to filter out fake content, are limited by their accuracy and their inability to fully capture the diverse interests of users.To address these challenges, we proposed PRISM-Protection-enhanced Recommendation with Interest-aware Sequential Modeling-a novel framework based on diffusion models.PRISM harnesses the generative and control capabilities of diffusion models to progressively learn the implicit distribution of user interests from their reading history, thereby generating personalized recommendations that align with both their linguistic preferences and interest domains.Furthermore, PRISM incorporates pre-trained authenticity representations as constraints during content generation, ensuring the credibility of the recommended news and effectively curbing the spread of fake news.Comprehensive evaluations from multiple dimensions demonstrate the superiority of our model.

The rapid development of social media has led to a surge of eye-catching fake news on the Internet, with multimodal news comprising both images and text being particularly prevalent. To address the challenges of Multimodal Fake News Detection (MFND), numerous supervised task-specific Multimodal Small Language Models (MSLMs) have been developed. However, these models lack the breadth of knowledge and the depth of language understanding, which results in unsatisfactory adaptability, generalization, and explainability performance. To address these issues, we attempt to introduce Large Vision-Language Models (LVLMs), aiming to leverage the common sense understanding and logical reasoning abilities of LVLMs for the MFND task. We observed that LVLMs can generate reasonable analyses of news content from specific angles. However, when it comes to synthesizing these analyses for final judgment, their performance declines significantly, failing to meet the accuracy benchmarks set by existing MSLMs detection models. This reflects the need for a more effective way for LVLMs, which have not undergone task-specific training, to utilize their knowledge and capabilities. Based on these findings, we propose the Explainable Adaptive Rationale-Augmented Multimodal (EARAM) framework, which adaptively uses MSLMs to extract useful rationales from the multi-perspective analyses of LVLMs. After making judgments based on these rationales, EARAM then assists LVLMs in generating more reliable explanations. Extensive experiments demonstrate that our model not only achieves state-of-the-art results on widely used datasets but also significantly outperforms other models in terms of generalization and explainability.

Dominant Person Search methods aim to localize and recognize query persons in a unified network, which jointly optimizes the two sub-tasks of pedestrian detection and Re-Identification (ReID). Despite significant progress, current methods face two primary challenges: 1) the pedestrian candidates learned within detectors are suboptimal for the ReID task. 2) the potential for collaboration between two sub-tasks is overlooked. To address these issues, we present a novel Person Search framework based on the Diffusion model, PSDiff. PSDiff formulates the person search as a dual denoising process from noisy boxes and ReID embeddings to ground truths. Distinct from the conventional Detection-to-ReID approach, our denoising paradigm discards prior pedestrian candidates generated by detectors, thereby avoiding the local optimum problem of the ReID task. Following the new paradigm, we further design a new Collaborative Denoising Layer (CDL) to optimize detection and ReID sub-tasks in an iterative and collaborative way, which makes two sub-tasks mutually beneficial. Extensive experiments on the standard benchmarks show that PSDiff achieves state-of-the-art performance with fewer parameters and elastic computing overhead.

Fake news data, often sampled from the same communities, results in the veracity of news being highly correlated with certain textual and visual entities. This correlation leads fake news classification models to be prone to shortcut learning, quickly overfitting by capturing only shallow spurious correlations between labels and features. Consequently, neural networks trained on such data suffer from poor generalization and potential misclassification under distribution shifts. To address these critical challenges and enhance the robustness of fake news detection, in this paper, we propose a DIsentanglement-based Causality-awarE fake news detection method (DICE). DICE introduces a novel paradigm that moves beyond merely mitigating known correlations or relying on predefined bias categories. Specifically, DICE dynamically constructs multimodal news into a graph neural network, employing learnable node and edge mask disentanglers to effectively model and separate genuine causal relationships from spurious correlations between multimodal features and veracity labels. To reinforce this disentanglement process, we design a novel optimization framework that minimizes extrapolation risk and enforces representation orthogonality, leading to robust disentangled causal and biased representations. Extensive experiments demonstrate that DICE achieves superior performance on five large-scale fake news detection benchmarks. Additionally, our evaluation on a heavily biased fake news dataset demonstrates DICE’s strong generalization, suggesting its potential to inform a new paradigm in causal fake news detection. The code repo is available: https://github.com/mazihan880/DICE Code/.

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of modality-invariant information (MII) and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal inputs for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL's efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses.

Cross-modal retrieval (CMR) aims to establish interaction between different modalities, among which supervised CMR is emerging due to its flexibility in learning semantic category discrimination. Despite the remarkable performance of previous supervised CMR methods, much of their success can be attributed to the well-annotated data. However, even for unimodal data, precise annotation is expensive and time-consuming, and it becomes more challenging with the multimodal scenario. In practice, massive multimodal data are collected from the Internet with coarse annotation, which inevitably introduces noisy labels. Training with such misleading labels would bring two key challenges-enforcing the multimodal samples to align incorrect semantics and widen the heterogeneous gap, resulting in poor retrieval performance. To tackle these challenges, this work proposes UOT-RCL, a unified framework based on optimal transport (OT) for robust CMR. First, we propose a semantic alignment based on partial OT to progressively correct the noisy labels, where a novel cross-modal consistent cost function is designed to blend different modalities and provide precise transport cost. Second, to narrow the discrepancy in multimodal data, an OT-based relation alignment is proposed to infer the semantic-level cross-modal matching. Both of these components leverage the inherent correlation among multimodal data to facilitate effective cost function. The experiments on three widely used CMR datasets demonstrate that our UOT-RCL surpasses the state-of-the-art approaches and significantly improves the robustness against noisy labels.

Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. Recently, to alleviate expensive data collection, co-occurring pairs from the Internet are automatically harvested for training. However, it inevitably includes mismatched pairs, i.e., noisy correspondences, undermining supervision reliability and degrading performance. Current methods leverage deep neural networks' memorization effect to address noisy correspondences, which overconfidently focus on similarity-guided training with hard negatives and suffer from self-reinforcing errors. In light of above, we introduce a novel noisy correspondence learning framework, namely Self-Reinforcing Errors Mitigation (SREM). Specifically, by viewing sample matching as classification tasks within the batch, we generate classification logits for the given sample. Instead of a single similarity score, we refine sample filtration through energy uncertainty and estimate model's sensitivity of selected clean samples using swapped classification entropy, in view of the overall prediction distribution. Additionally, we propose cross-modal biased complementary learning to leverage negative matches overlooked in hard-negative training, further improving model optimization stability and curbing self-reinforcing errors. Extensive experiments on challenging benchmarks affirm the efficacy and efficiency of SREM.

Despite significant progress in Text-to-Image (T2I) generative models, even lengthy and complex text descriptions still struggle to convey detailed controls. In contrast, Layout-to-Image (L2I) generation, aiming to generate realistic and complex scene images from user-specified layouts, has risen to prominence. However, existing methods transform layout information into tokens or RGB images for conditional control in the generative process, leading to insufficient spatial and semantic controllability of individual instances. To address these limitations, we propose a novel Spatial-Semantic Map Guided (SSMG) diffusion model that adopts the feature map, derived from the layout, as guidance. Owing to rich spatial and semantic information encapsulated in well-designed feature maps, SSMG achieves superior generation quality with sufficient spatial and semantic controllability compared to previous works. Additionally, we propose the Relation-Sensitive Attention (RSA) and Location-Sensitive Attention (LSA) mechanisms. The former aims to model the relationships among multiple objects within scenes while the latter is designed to heighten the model's sensitivity to the spatial information embedded in the guidance. Extensive experiments demonstrate that SSMG achieves highly promising results, setting a new state-of-the-art across a range of metrics encompassing fidelity, diversity, and controllability.

Social media bot detection has always been an arms race between advancements in machine learning bot detectors and adversarial bot strategies to evade detection.In this work, we bring the arms race to the next level by investigating the opportunities and risks of state-of-the-art large language models (LLMs) in social bot detection.To investigate the opportunities, we design novel LLM-based bot detectors by proposing a mixture-of-heterogeneous-experts framework to divide and conquer diverse user information modalities.To illuminate the risks, we explore the possibility of LLM-guided manipulation of user textual and structured information to evade detection.Extensive experiments with three LLMs on two datasets demonstrate that instruction tuning on merely 1,000 annotated examples produces specialized LLMs that outperform state-of-the-art bot detection baselines by up to 9.1% on both datasets.On the other hand, LLM-guided manipulation strategies could significantly bring down the performance of existing bot detectors by up to 29.6% and harm the calibration and reliability of bot detection systems.Ultimately, this works identifies LLMs as the new frontier of social bot detection research.1

The swift detection of multimedia fake news has emerged as a crucial task in combating malicious propaganda and safeguarding the security of the online environment.While existing methods have achieved commendable results in modeling entity-level inconsistency, addressing event-level inconsistency following the inherent subject-predicate logic of news and robustly learning news representations from poorquality news samples remain two challenges.In this paper, we propose an Event-dRiven fAke news Detection frAmewoRk (Event-Radar) based on multi-view learning, which integrates visual manipulation, textual emotion and multimodal inconsistency at event-level for fake news detection.Specifically, leveraging the capability of graph structures to capture interactions between events and parameters, Event-Radar captures event-level multimodal inconsistency by constructing an event graph that includes multimodal entity subject-predicate logic.Additionally, to mitigate the interference of poor-quality news, Event-Radar introduces a multi-view fusion mechanism, learning comprehensive and robust representations by computing the credibility of each view as a clue, thereby detecting fake news.Extensive experiments demonstrate that Event-Radar achieves outstanding performance on three large-scale fake news detection benchmarks.Our studies also confirm that Event-Radar exhibits strong robustness, providing a paradigm for detecting fake news from noisy news samples.

Collecting well-matched multimedia datasets is crucial for training cross-modal retrieval models. However, in real-world scenarios, massive multimodal data are harvested from the Internet, which inevitably contains Partially Mis-matched Pairs (PMPs). Undoubtedly, such semantical irrelevant data will remarkably harm the cross-modal retrieval performance. Previous efforts tend to mitigate this problem by estimating a soft correspondence to down-weight the contribution of PMPs. In this paper, we aim to address this challenge from a new perspective: the potential semantic similarity among unpaired samples makes it possible to excavate useful knowledge from mismatched pairs. To achieve this, we propose L2RM, a general framework based on Optimal Transport (OT) that learns to rematch mismatched pairs. In detail, L2RM aims to generate refined alignments by seeking a minimal-cost transport plan across different modalities. To formalize the rematching idea in OT, first, we propose a self-supervised cost function that automatically learns from explicit similarity-cost mapping relation. Second, we present to model a partial OT problem while restricting the transport among false positives to further boost refined alignments. Extensive experiments on three benchmarks demonstrate our L2RM significantly improves the robustness against PMPs for existing models. The code is available at https://github.com/hhc1997/L2RM.

Transformer architecture search (TAS) has achieved remarkable progress in automating the neural architecture design process of vision transformers. Recent TAS advancements have discovered outstanding transformer architectures while saving tremendous labor from human experts. However, it is still cumbersome to deploy these methods in real-world applications due to the expensive costs of data labeling under the supervised learning paradigm. To this end, this paper proposes a masked image modelling (MIM) based self-supervised neural architecture search method specifically designed for vision transformers, termed as MaskTAS, which completely avoids the expensive costs of data labeling inherited from supervised learning. Based on the one-shot NAS framework, MaskTAS requires to train various weight-sharing subnets, which can easily diverged without strong supervision in MIM-based self-supervised learning. For this issue, we design the search space of MaskTAS as a siamesed teacher-student architecture to distill knowledge from pre-trained networks, allowing for efficient training of the transformer supernet. To achieve self-supervised transformer architecture search, we further design a novel unsupervised evaluation metric for the evolutionary search algorithm, where each candidate of the student branch is rated by measuring its consistency with the larger teacher network. Extensive experiments demonstrate that the searched architectures can achieve state-of-the-art accuracy on CIFAR-10, CIFAR-100, and ImageNet datasets even without using manual labels. Moreover, the proposed MaskTAS can generalize well to various data domains and tasks by searching specialized transformer architectures in self-supervised manner.

Fairness-aware graph neural networks (GNNs) have gained a surge of attention as they can reduce the bias of predictions on any demographic group (e.g., female) in graph-based applications. Although these methods greatly improve the algorithmic fairness of GNNs, the fairness can be easily corrupted by carefully designed adversarial attacks. In this paper, we investigate the problem of adversarial attacks on fairness of GNNs and propose G-FairAttack, a general framework for attacking various types of fairness-aware GNNs in terms of fairness with an unnoticeable effect on prediction utility. In addition, we propose a fast computation technique to reduce the time complexity of G-FairAttack. The experimental study demonstrates that G-FairAttack successfully corrupts the fairness of different types of GNNs while keeping the attack unnoticeable. Our study on fairness attacks sheds light on potential vulnerabilities in fairness-aware GNNs and guides further research on the robustness of GNNs in terms of fairness.

Detecting fake news on social media has become a crucial task in combating online misinformation and countering malicious propaganda. Existing methods rely on semantic consistency across modalities to fuse features and determine news authenticity. However, cunning fake news publisher manipulate image to ensure a high level of semantic consistency between news post and image, making it more difficult to distinguish fake news. To this end, we propose MHFFD (Mixed High-Frequency Feature Detector), a novel fake news detection framework that utilizes token-level semantic consistency evaluation to identify key elements in news content and provide guidance for discovering image manipulation and learning better news representations. Extensive experiments demonstrate that MHFFD outperforms state-of-the-art methods on two widely used fake news detection datasets. Further research also validates the effectiveness of token-level semantic alignment and manipulation detection.

Short videos turn into an important channel for public sharing, as well as they've become a fertile ground for fake news. Fake news video detection is to judge the veracity of news based on its different modal information, such as video, audio, text, image and social context information. Current detection models tend to learn the multimodal dataset biases within spurious correlations between news modalities and veracity labels as shortcuts, rather than learning how to integrate the multimodal information behind them to reason, resulting in seriously degrading their detection and generalization capabilities. To address this issues, we propose a Multimodal Multi-View Debiasing (MMVD) framework, which makes the first attempt to mitigate various multimodal biases for fake news video detection. Inspired by people's misleading situations by multimodal short videos, we summarize three cognitive biases: static, dynamic and social biases. MMVD put forward a multi-view causal reasoning strategy to learn unbiased dependencies within the cognitive biases, thus enhancing the unbiased prediction of multimodal videos. The extensive experimental results show that the MMVD could improve the detection performance of multimodal fake news video. Studies also confirm that our MMVD can mitigate multiple biases on complex real-world scenarios and improve generalization ability of fake news video detection.

As malicious actors employ increasingly advanced and widespread bots to disseminate misinformation and manipulate public opinion, the detection of Twitter bots has become a crucial task. Though graph-based Twitter bot detection methods achieve state-of-the-art performance, we find that their inference depends on the neighbor users multi-hop away from the targets, and fetching neighbors is time-consuming and may introduce sampling bias. At the same time, our experiments reveal that after finetuning on Twitter bot detection task, pretrained language models achieve competitive performance while do not require a graph structure during deployment. Inspired by this finding, we propose a novel bot detection framework LMBot that distills the graph knowledge into language models (LMs) for graph-less deployment in Twitter bot detection to combat data dependency challenge. Moreover, LMBot is compatible with graph-based and graph-less datasets. Specifically, we first represent each user as a textual sequence and feed them into the LM for domain adaptation. For graph-based datasets, the output of LM serves as input features for the GNN, enabling LMBot to optimize for bot detection and distill knowledge back to the LM in an iterative, mutually enhancing process. Armed with the LM, we can perform graph-less inference with graph knowledge, which resolves the graph data dependency and sampling bias issues. For datasets without graph structure, we simply replace the GNN with an MLP, which also shows strong performance. Our experiments demonstrate that LMBot achieves state-of-the-art performance on four Twitter bot detection benchmarks. Extensive studies also show that LMBot is more robust, versatile, and efficient compared to existing graph-based Twitter bot detection methods.

Zero-shot object detection (ZSD), the task that extends conventional detection models to detecting objects from unseen categories, has emerged as a new challenge in computer vision. Most existing approaches tackle the ZSD task with a strict mapping-transfer strategy that may lead to suboptimal ZSD results: 1) the learning process of these models neglects the available semantic information on unseen classes, which can easily bias towards the seen categories; 2) the original visual feature space is not well-structured for the ZSD task due to the lack of discriminative information. To address these issues, we develop a novel Semantics-Guided Contrastive Network for ZSD, named ContrastZSD, a detection framework that first brings contrastive learning mechanism into the realm of zero-shot detection. Particularly, ContrastZSD incorporates two semantics-guided contrastive learning subnets that contrast between region-category and region-region pairs respectively. The pairwise contrastive tasks take advantage of supervision signals derived from both the ground truth label and class similarity information. By performing supervised contrastive learning over those explicit semantic supervision, the model can learn more knowledge about unseen categories to avoid the bias problem to seen concepts, while optimizing the visual data structure to be more discriminative for better visual-semantic alignment. Extensive experiments are conducted on two popular benchmarks for ZSD, i.e., PASCAL VOC and MS COCO. Results show that our method outperforms the previous state-of-the-art on both ZSD and generalized ZSD tasks.

Encoding only the task-related information from the raw data, i.e., disentangled representation learning, can greatly contribute to the robustness and generalizability of models. Although significant advances have been made by regularizing the information in representations with information theory, two major challenges remain: 1) the representation compression inevitably leads to performance drop; 2) the disentanglement constraints on representations are in complicated optimization. To these issues, we introduce Bayesian networks with transmitted information to formulate the interaction among input and representations during disentanglement. Building upon this framework, we propose DisTIB (Transmitted Information Bottleneck for Disentangled representation learning), a novel objective that navigates the balance between information compression and preservation. We employ variational inference to derive a tractable estimation for DisTIB. This estimation can be simply optimized via standard gradient descent with a reparameterization trick. Moreover, we theoretically prove that DisTIB can achieve optimal disentanglement, underscoring its superior efficacy. To solidify our claims, we conduct extensive experiments on various downstream tasks to demonstrate the appealing efficacy of DisTIB and validate our theoretical analyses.

Few-shot learning (FSL) poses a significant challenge in classifying unseen classes with limited samples, primarily stemming from the scarcity of data. Although numerous generative approaches have been investigated for FSL, their generation process often results in entangled outputs, exacerbating the distribution shift inherent in FSL. Consequently, this considerably hampers the overall quality of the generated samples. Addressing this concern, we present a pioneering framework called DisGenIB, which leverages an Information Bottleneck (IB) approach for Disentangled Generation. Our framework ensures both discrimination and diversity in the generated samples, simultaneously. Specifically, we introduce a groundbreaking Information Theoretic objective that unifies disentangled representation learning and sample generation within a novel framework. In contrast to previous IB-based methods that struggle to leverage priors, our proposed DisGenIB effectively incorporates priors as invariant domain knowledge of sub-features, thereby enhancing disentanglement. This innovative approach enables us to exploit priors to their full potential and facilitates the overall disentanglement process. Moreover, we establish the theoretical foundation that reveals certain prior generative and disentanglement methods as special instances of our DisGenIB, underscoring the versatility of our proposed framework. To solidify our claims, we conduct comprehensive experiments on demanding FSL benchmarks, affirming the remarkable efficacy and superiority of DisGenIB. Furthermore, the validity of our theoretical analyses is substantiated by the experimental results. Our code is available at https://github.com/eric-hang/DisGenIB.

Semi-supervised graph learning aims to improve learning performance by leveraging unlabeled nodes. Typically, it can be approached in two different ways, includingpredictive representation learning(PRL) where unlabeled data provide clues on input distribution andlabel-dependent regularization(LDR) which smooths the output distribution with unlabeled nodes to improve generalization. However, most existing PRL approaches suffer from overfitting in an end-to-end setting or cannot encode task-specific information when used as unsupervised pre-training (i.e., two-stage learning). Meanwhile, LDR strategies often introduce redundant and invalid data perturbations that can slow down and mislead the training. To address all these issues, we propose a general framework SemiGraL for semi-supervised learning on graphs, which bridges and facilitates both PRL and LDR in a single shot. By extending a contrastive learning architecture to the semi-supervised setting, we first develop asemi-supervised contrastive representation learningprocess with virtual adversarial augmentation to map input nodes into a label-preserving representation space while avoiding overfitting. We then introduce amultiview consistency classificationprocess with well-constrained perturbations to achieve adversarially robust classification. Extensive experiments on seven semi-supervised node classification benchmark datasets show that SemiGraL outperforms various baselines while enjoying strong generalization and robustness performance.

Recent studies have revealed that GNNs are vulnerable to adversarial attacks. Most existing robust graph learning methods measure model robustness based on label information, rendering them infeasible when label information is not available. A straightforward direction is to employ the widely used Infomax technique from typical Unsupervised Graph Representation Learning (UGRL) to learn robust unsupervised representations. Nonetheless, directly transplanting the Infomax technique from typical UGRL to robust UGRL may involve a biased assumption. In light of the limitation of Infomax, we propose a novel unbiased robust UGRL method calledRobust Graph Information Bottleneck(RGIB), which is grounded in the Information Bottleneck (IB) principle. Our RGIB attempts to learn robust node representations against adversarial perturbations by preserving the original information in the benign graph while eliminating the adversarial information in the adversarial graph. There are mainly two challenges to optimizing RGIB: 1) high complexity of adversarial attack to perturb node features and graph structure jointly in the training procedure; 2) mutual information estimation upon adversarially attacked graphs. To tackle these problems, we further propose an efficient adversarial training strategy with only feature perturbations and an effective mutual information estimator with the subgraph-level summary. Moreover, we theoretically establish a connection between our proposed RGIB and the robustness of downstream classifiers, revealing that RGIB can provide a lower bound on the adversarial risk of downstream classifiers. Extensive experiments over several benchmarks and downstream tasks demonstrate the effectiveness and superiority of our proposed method.

Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the model. Although various multi-modal learning methods have been proposed and offer remarkable recognition results, almost all of these methods rely on high-quality manual annotations and assume that modalities among multi-modal data provide semantically relevant information. Unfortunately, the widely used video datasets are usually coarse-annotated or collected from the Internet. Thus, it inevitably contains a portion of noisy labels and noisy correspondence. To address this challenge, we use the audio-visual action recognition task as a proxy and propose a noise-tolerant learning framework to find anti-interference model parameters against both noisy labels and noisy correspondence. Specifically, our method consists of two phases that aim to rectify noise by the inherent correlation between modalities. First, a noise-tolerant contrastive training phase is performed to make the model immune to the possible noisy-labeled data. Despite the benefits brought by contrastive training, it would overfit the noisy correspondence and thus provide false supervision. To alleviate the influence of noisy correspondence, we propose a cross-modal noise estimation component to adjust the consistency between different modalities. As the noisy correspondence existed at the instance level, we further propose a category-level contrastive loss to reduce its interference. Second, in the hybrid-supervised training phase, we calculate the distance metric among features to obtain corrected labels, which are used as complementary supervision to guide the training. Furthermore, due to the lack of suitable datasets, we establish a benchmark of real-world noisy correspondence in audio-visual data by relabeling the Kinetics dataset. Extensive experiments on a wide range of noisy levels demonstrate that our method significantly improves the robustness of the action recognition model and surpasses the baselines by a clear margin.

Zhenyu Lei, Herun Wan, Wenqian Zhang, Shangbin Feng, Zilong Chen, Jundong Li, Qinghua Zheng, Minnan Luo. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Despite the success of multimodal learning in crossmodal retrieval task, the remarkable progress relies on the correct correspondence among multimedia data. However, collecting such ideal data is expensive and time-consuming. In practice, most widely used datasets are harvested from the Internet and inevitably contain mismatched pairs. Training on such noisy correspondence datasets causes performance degradation because the cross-modal retrieval methods can wrongly enforce the mismatched data to be similar. To tackle this problem, we propose a Meta Similarity Correction Network (MSCN) to provide reliable similarity scores. We view a binary classification task as the meta-process that encourages the MSCN to learn discrimination from positive and negative meta-data. To further alleviate the influence of noise, we design an effective data purification strategy using meta-data as prior knowledge to remove the noisy samples. Extensive experiments are conducted to demonstrate the strengths of our method in both synthetic and real-world noises, including Flickr30K, MS-COCO, and Conceptual Captions. Our code is publicly available.11https://github.com/hhc1997/MSCN

Online movie review platforms are providing crowdsourced feedback for the film industry and the general public, while spoiler reviews greatly compromise user experience.Although preliminary research efforts were made to automatically identify spoilers, they merely focus on the review content itself, while robust spoiler detection requires putting the review into the context of facts and knowledge regarding movies, user behavior on film review platforms, and more.In light of these challenges, we first curate a large-scale networkbased spoiler detection dataset LCS and a comprehensive and up-to-date movie knowledge base UKM.We then propose MVSD, a novel Multi-View Spoiler Detection framework that takes into account the external knowledge about movies and user activities on movie review platforms.Specifically, MVSD constructs three interconnecting heterogeneous information networks to model diverse data sources and their multi-view attributes, while we design and employ a novel heterogeneous graph neural network architecture for spoiler detection as node-level classification.Extensive experiments demonstrate that MVSD advances the state-of-the-art on two spoiler detection datasets, while the introduction of external knowledge and user interactions help ground robust spoiler detection.Our data and code are available at https://github.com/Arthur-

Person search aims to locate a query person in a gallery of unconstrained scene images, which has many real-world applications. However, existing methods directly build off of advances in object detection for better performance rather than efficiency. Complex designs in heavy-weight detectors are redundant for person search. Furthermore, challenges in person search force existing methods to employ additional modules, which greatly deteriorates models’ efficiency. In this paper, we propose a novel real-time framework for both effective and efficient person search, termed as InvarPS. InvarPS optimizes the over-designed network with invariant feature learning. Specifically, considering the main challenges (i.e., appearance changes, scale variations, and conflicting tasks) in person search, we propose an improved backbone, a Single-Scale Feature Fusion (SSFF) module and a Hierarchical Decoupling Head (HDH) to facilitate the model learning appearance, scale, and task invariant features, respectively. Extensive experiments demonstrate that our method achieves state-of-the-art performance with real-time speed (>100 FPS), which is significantly faster than any previous competitive approach.

Many existing anomaly detection methods on attributed networks do not seriously tackle the inherent multi-view property in attribute space but concatenate multiple views into a single feature vector, which inevitably ignores the incompatibility between heterogeneous views caused by their own statistical properties. In practice, the distinct but complementary information brought by multi-view data promises the potential for more effective anomaly detection than the efforts only based on single-view data. Furthermore, abnormal patterns naturally behave diversely in different views, which coincides with people’s desire to discover specific abnormalities according to their preferences for views (attributes). Most existing methods cannot adapt to people’s requirements as they fail to consider the idiosyncrasy of user preferences. Thus, in this paper, we propose a multi-view framework ALARM to incorporate user preferences into anomaly detection and simultaneously tackle heterogeneous attribute characteristics through multiple graph encoders and a well-designed aggregator that supports self-learning and user-guided learning. Experiments on synthetic and real-world datasets corroborate the desirable performance of ALARM and its effectiveness in supporting user-oriented anomaly detection.

Researchers recently investigated to explain Graph Neural Networks (GNNs) on the access to a task-specific GNN, which may hinder their wide applications in practice. Specifically, task-specific explanation methods are incapable of explaining pretrained GNNs whose downstream tasks are usually inaccessible, not to mention giving explanations for the transferable knowledge in pretrained GNNs. Additionally, task-specific methods only consider target models' output in the label space, which are coarse-grained and insufficient to reflect the model's internal logic. To address these limitations, we consider a two-stage explanation strategy, i.e., explainers are first pretrained in a task-agnostic fashion in the representation space and then further fine-tuned in the task-specific label space and representation space jointly if downstream tasks are accessible. The two-stage explanation strategy endows post-hoc graph explanations with the applicability to pretrained GNNs where downstream tasks are inaccessible and the capacity to explain the transferable knowledge in the pretrained GNNs. Moreover, as the two-stage explanation strategy explains the GNNs in the representation space, the fine-grained information in the representation space also empowers the explanations. Furthermore, to achieve a trade-off between the fidelity and intelligibility of explanations, we propose an explanation framework based on the Information Bottleneck principle, named Explainable Graph Information Bottleneck (EGIB). EGIB subsumes the task-specific explanation and task-agnostic explanation into a unified framework. To optimize EGIB objective, we derive a tractable bound and adopt a simple yet effective explanation generation architecture. Based on the unified framework, we further theoretically prove that task-agnostic explanation is a relaxed sufficient condition of task-specific explanation, which indicates the transferability of task-agnostic explanations. Extensive experimental results demonstrate the effectiveness of our proposed explanation method.

Twitter bot detection has become a crucial task in efforts to combat online misinformation, mitigate election interference, and curb malicious propaganda. However, advanced Twitter bots often attempt to mimic the characteristics of genuine users through feature manipulation and disguise themselves to fit in diverse user communities, posing challenges for existing Twitter bot detection models. To this end, we propose BotMoE, a Twitter bot detection framework that jointly utilizes multiple user information modalities (metadata, textual content, network structure) to improve the detection of deceptive bots. Furthermore, BotMoE incorporates a community-aware Mixture-of-Experts (MoE) layer to improve domain generalization and adapt to different Twitter communities. Specifically, BotMoE constructs modal-specific encoders for metadata features, textual content, and graph structure, which jointly model Twitter users from three modal-specific perspectives. We then employ a community-aware MoE layer to automatically assign users to different communities and leverage the corresponding expert networks. Finally, user representations from metadata, text, and graph perspectives are fused with an expert fusion layer, combining all three modalities while measuring the consistency of user information. Extensive experiments demonstrate that BotMoE significantly advances the state-of-the-art on three Twitter bot detection benchmarks. Studies also confirm that BotMoE captures advanced and evasive bots, alleviates the reliance on training data, and better generalizes to new and previously unseen user communities.

Knowledge Graph Embeddings (KGE) aim to map entities and relations to low dimensional spaces and have become the de-facto standard for knowledge graph completion. Most existing KGE methods suffer from the sparsity challenge, where it is harder to predict entities that appear less frequently in knowledge graphs. In this work, we propose a novel framework KRACL1 to alleviate the widespread sparsity in KGs with graph context and contrastive learning. Firstly, we propose the Knowledge Relational Attention Network (KRAT) to leverage the graph context by simultaneously projecting neighboring triples to different latent spaces and jointly aggregating messages with the attention mechanism. KRAT is capable of capturing the subtle semantic information and importance of different context triples as well as leveraging multi-hop information in knowledge graphs. Secondly, we propose the knowledge contrastive loss by combining the contrastive loss with cross entropy loss, which introduces more negative samples and thus enriches the feedback to sparse entities. Our experiments demonstrate that KRACL achieves superior results across various standard knowledge graph benchmarks, especially on WN18RR and NELL-995 which have large numbers of low in-degree entities. Extensive experiments also bear out KRACL’s effectiveness in handling sparse knowledge graphs and robustness against noisy triples.

The rich content in various real-world networks such as social networks, biological networks, and communication networks provides unprecedented opportunities for unsupervised machine learning on graphs. This paper investigates the fundamental problem of preserving and extracting abundant information from graph-structured data into embedding space without external supervision. To this end, we generalize conventional mutual information computation from vector space to graph domain and present a novel concept, Graphical Mutual Information (GMI), to measure the correlation between input graph and hidden representation. Except for standard GMI which considers graph structures from a local perspective, our further proposed GMI++ additionally captures global topological properties by analyzing the co-occurrence relationship of nodes. GMI and its extension exhibit several benefits: First, they are invariant to the isomorphic transformation of input graphs-an inevitable constraint in many existing methods; Second, they can be efficiently estimated and maximized by current mutual information estimation methods; Lastly, our theoretical analysis confirms their correctness and rationality. With the aid of GMI, we develop an unsupervised embedding model and adapt it to the specific anomaly detection task. Extensive experiments indicate that our GMI methods achieve promising performance in various downstream tasks, such as node classification, link prediction, and anomaly detection.

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training still need to be detected. We design an end-to-end deep transferable network TN-ZSTAD as the architecture for this solution. On the one hand, this network utilizes an activity graph transformer to predict a set of activity instances that appear in the video, rather than produces many activity proposals in advance. On the other hand, this network captures the common semantics of seen and unseen activities from their corresponding label embeddings, and it is optimized with an innovative loss function that considers the classification property on seen activities and the transfer property on unseen activities together. Experiments on the THUMOS'14, Charades, and ActivityNet datasets show promising performance in terms of detecting unseen activities.

Few-shot learning (FSL) that aims to recognize novel classes with few labeled samples is troubled by its data scarcity. Though recent works tackle FSL with data augmentation-based methods, these models fail to maintain the discrimination and diversity of the generated samples due to the distribution shift and intra-class bias caused by the data scarcity, therefore greatly undermining the performance. To this end, we use causal mechanisms, which are constant among independent variables across data distribution, to alleviate such effects. In this sense, we decompose the image information into two independent components: sample-specific and class-agnostic information, and further propose a novel Counterfactual Generation Framework (CGF) to learn the underlying causal mechanisms to synthesize faithful samples for FSL. Specifically, based on the counterfactual inference, we design a class-agnostic feature extractor to capture the sample-specific information, together with a counterfactual generation network to simulate the data generation process from a causal perspective. Moreover, to leverage the power of CGF in counterfactual inference, we further develop a novel classifier that classifies samples based on their distributions of counterfactual generations. Extensive experiments demonstrate the effectiveness of CGF on four FSL benchmarks, e.g., 80.12/86.13% accuracy on 5-way 1/5-shot miniImageNet FSL tasks, significantly improving the performance. Our codes and models are available athttps://github.com/eric-hang/CGF.

Weakly supervised person search involves training a model with only bounding box annotations, without human-annotated identities. Clustering algorithms are commonly used to assign pseudo-labels to facilitate this task. However, inaccurate pseudo-labels and imbalanced identity distributions can result in severe label and sample noise. In this work, we propose a novel Collaborative Contrastive Refining (CCR) weakly-supervised framework for person search that jointly refines pseudo-labels and the sample-learning process with different contrastive strategies. Specifically, we adopt a hybrid contrastive strategy that leverages both visual and context clues to refine pseudo-labels, and leverage the sample-mining and noise-contrastive strategy to reduce the negative impact of imbalanced distributions by distinguishing positive samples and noise samples. Our method brings two main advantages: 1) it facilitates better clustering results for refining pseudo-labels by exploring the hybrid similarity; 2) it is better at distinguishing query samples and noise samples for refining the sample-learning process. Extensive experiments demonstrate the superiority of our approach over the state-of-the-art weakly supervised methods by a large margin (more than 3% mAP on CUHK-SYSU). Moreover, by leveraging more diverse unlabeled data, our method achieves comparable or even better performance than the state-of-the-art supervised methods.

Twitter bot detection has become an important and challenging task to combat misinformation and protect the integrity of the online discourse. State-of-the-art approaches generally leverage the topological structure of the Twittersphere, while they neglect the heterogeneity of relations and influence among users. In this paper, we propose a novel bot detection framework to alleviate this problem, which leverages the topological structure of user-formed heterogeneous graphs and models varying influence intensity between users. Specifically, we construct a heterogeneous information network with users as nodes and diversified relations as edges. We then propose relational graph transformers to model heterogeneous influence between users and learn node representations. Finally, we use semantic attention networks to aggregate messages across users and relations and conduct heterogeneity-aware Twitter bot detection. Extensive experiments demonstrate that our proposal outperforms state-of-the-art methods on a comprehensive Twitter bot detection benchmark. Additional studies also bear out the effectiveness of our proposed relational graph transformers, semantic attention networks and the graph-based approach in general.

Current Graph Neural Networks (GNNs) suffer from the over-smoothing problem, which results in indistinguishable node representations and low model performance with more GNN layers. Many methods have been put forward to tackle this problem in recent years. However, existing tackling over-smoothing methods emphasize model performance and neglect the over-smoothness of node representations. Additional, different approaches are applied one at a time, while there lacks an overall framework to jointly leverage multiple solutions to the over-smoothing challenge. To solve these problems, we propose GraTO, a framework based on neural architecture search to automatically search for GNNs architecture. GraTO adopts a novel loss function to facilitate striking a balance between model performance and representation smoothness. In addition to existing methods, our search space also includes DropAttribute, a novel scheme for alleviating the over-smoothing challenge, to fully leverage diverse solutions. We conduct extensive experiments on six real-world datasets to evaluate GraTo, which demonstrates that GraTo outperforms baselines in the over-smoothing metrics and achieves competitive performance in accuracy. GraTO is especially effective and robust with increasing numbers of GNN layers. Further experiments bear out the quality of node representations learned with GraTO and the effectiveness of model architecture. We make the code of GraTo available at Github (https://github.com/fxsxjtu/GraTO).

Shangbin Feng, Zhaoxuan Tan, Zilong Chen, Ningnan Wang, Peisheng Yu, Qinghua Zheng, Xiaojun Chang, Minnan Luo. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.

In this paper, we study the digital marketing where marketing officers (MOs) have to commit to creating brand new promotion ads/contents based on understandings of users' needs or preferences. Users' behaviors are typically high dimensional and hard to understand. Therefore, dimension reduction of users' behaviors from high dimensions and explainability are important to help MOs launch operation-friendly marketings. As such, it is natural to exploit topic models to help MOs understand users' intents from users' behaviors (e.g., user-item visits) in case we treat each user as a document and users' behaviors of visiting an item as a word. However, users of low activities and items followed by power law distributions are common in user-item visit data, which pose significant challenges to traditional topic models. We present a social and semantic enhanced topic model (S2TM) for users' intent mining. We optimize the user-intent estimates based on a graph neural network atop of a social network, and optimize the intent-item estimates based on a skip-gram word embedding approach by linking the semantics of items to pre-trained word embeddings. We propose an efficient stochastic vari-ational inference algorithm for the inference of latent variables and learning of parameters. Extensive experiments on real-world data show the effectivenesses of S2TM in terms of perplexities, topic coherence and semantic coherence compared with state-of-the-art topic models. We further show how MOs interact with our operation-friendly intent mining system, and results on real-world marketing campaigns in terms of click-through rate at Alipay.

Wenqian Zhang, Shangbin Feng, Zilong Chen, Zhenyu Lei, Jundong Li, Minnan Luo. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Twitter bot detection has become an increasingly important task to combat misinformation, facilitate social media moderation, and preserve the integrity of the online discourse. State-of-the-art bot detection methods generally leverage the graph structure of the Twitter network, and they exhibit promising performance when confronting novel Twitter bots that traditional methods fail to detect. However, very few of the existing Twitter bot detection datasets are graph-based, and even these few graph-based datasets suffer from limited dataset scale, incomplete graph structure, as well as low annotation quality. In fact, the lack of a large-scale graph-based Twitter bot detection benchmark that addresses these issues has seriously hindered the development and evaluation of novel graph-based bot detection approaches. In this paper, we propose TwiBot-22, a comprehensive graph-based Twitter bot detection benchmark that presents the largest dataset to date, provides diversified entities and relations on the Twitter network, and has considerably better annotation quality than existing datasets. In addition, we re-implement 35 representative Twitter bot detection baselines and evaluate them on 9 datasets, including TwiBot-22, to promote a fair comparison of model performance and a holistic understanding of research progress. To facilitate further research, we consolidate all implemented codes and datasets into the TwiBot-22 evaluation framework, where researchers could consistently evaluate new models and datasets. The TwiBot-22 Twitter bot detection benchmark and evaluation framework are publicly available at \url{https://twibot22.github.io/}.

Abstract Entity alignment (EA) aims to discover the equivalent entities in different knowledge graphs (KGs). It is a pivotal step for integrating KGs to increase knowledge coverage and quality. Recent years have witnessed a rapid increase of EA frameworks. However, state-of-the-art solutions tend to rely on labeled data for model training. Additionally, they work under the closed-domain setting and cannot deal with entities that are unmatchable. To address these deficiencies, we offer an unsupervised framework that performs entity alignment in the open world. Specifically, we first mine useful features from the side information of KGs. Then, we devise an unmatchable entity prediction module to filter out unmatchable entities and produce preliminary alignment results. These preliminary results are regarded as the pseudo-labeled data and forwarded to the progressive learning framework to generate structural representations, which are integrated with the side information to provide a more comprehensive view for alignment. Finally, the progressive learning framework gradually improves the quality of structural embeddings and enhances the alignment performance. Furthermore, noticing that the pseudo-labeled data are of various qualities, we introduce the concept of confidence to measure the probability of an entity pair of being true and develop a confidence-based unsupervised EA framework . Our solutions do not require labeled data and can effectively filter out unmatchable entities. Comprehensive experimental evaluations validate the superiority of our proposals .

Community detection is one of the fundamental tasks in graph mining, which aims to identify group assignment of nodes in a complex network. Recently, network embedding techniques have demonstrated their strong power in advancing the community detection task and achieve better performance than various traditional methods. Despite their empirical success, most of the existing algorithms directly leverage the observed coarse network structure for community detection. Therefore, they often lead to suboptimal performance as the observed connections fail to capture the essential tie strength information among nodes precisely and account for the impact of noisy links. In this paper, an optimal network structure for community detection is introduced to characterize the fine-grained tie strength information between connected nodes and alleviate the adverse effects of noisy links. To obtain an expressive node representation for community detection, we learn the optimal network structure and network embeddings in a joint framework, instead of using a two-stage approach to derive the node embeddings from the coarse network topology. In particular, we formulate the joint framework as an optimization problem and an alternating optimization algorithm is exploited to solve the proposed optimization problem. Additionally, theoretical analyses regarding the computational complexity and the convergence of the optimization algorithm are also provided. Extensive experiments on both synthetic and real-world networks demonstrate the effectiveness and superiority of the proposed framework.

The explosion of modeling complex systems using attributed networks boosts the research on anomaly detection in such networks, which can be applied in various high-impact domains. Many existing attempts, however, do not seriously tackle the inherent multi-view property in attribute space but concatenate multiple views into a single feature vector, which inevitably ignores the incompatibility between heterogeneous views caused by their own statistical properties. Actually, the distinct but complementary information brought by multi-view data promises the potential for more effective anomaly detection than the efforts only based on single-view data. Furthermore, the abnormal patterns naturally behave diversely in different views, which coincides with people’s desire to discover specific abnormality according to their preferences for views (attributes). Most existing methods cannot adapt to people’s requirements as they fail to consider the idiosyncrasy of user preferences. Therefore, we propose a multi-view frameworkAlarmto incorporate user preferences into anomaly detection and simultaneously tackle heterogeneous attribute characteristics through multiple graph encoders and a well-designed aggregator that supports self-learning and user-guided learning. Experiments on synthetic and real-world datasets, e.g., Disney, Books, and Enron, corroborate the improvement ofAlarmin detection accuracy evaluated by the AUC metric and its effectiveness in supporting user-oriented anomaly detection.

Twitter bot detection is an important and challenging task. Existing bot detection measures fail to address the challenge of community and disguise, falling short of detecting bots that disguise as genuine users and attack collectively. To address these two challenges of Twitter bot detection, we propose BotRGCN, which is short for Bot detection with Relational Graph Convolutional Networks. BotRGCN addresses the challenge of community by constructing a heterogeneous graph from follow relationships and applies relational graph convolutional networks. Apart from that, BotRGCN makes use of multi-modal user semantic and property information to avoid feature engineering and augment its ability to capture bots with diversified disguise. Extensive experiments demonstrate that BotRGCN outperforms competitive baselines on a comprehensive benchmark TwiBot-20 which provides follow relationships.

Twitter has become a major social media platform since its launching in 2006, while complaints about bot accounts have increased recently. Although extensive research efforts have been made, the state-of-the-art bot detection methods fall short of generalizability and adaptability. Specifically, previous bot detectors leverage only a small fraction of user information and are often trained on datasets that only cover few types of bots. As a result, they fail to generalize to real-world scenarios on the Twittersphere where different types of bots co-exist. Additionally, bots in Twitter are constantly evolving to evade detection. Previous efforts, although effective once in their context, fail to adapt to new generations of Twitter bots. To address the two challenges of Twitter bot detection, we propose SATAR, a self-supervised representation learning framework of Twitter users, and apply it to the task of bot detection. In particular, SATAR generalizes by jointly leveraging the semantics, property and neighborhood information of a specific user. Meanwhile, SATAR adapts by pre-training on a massive number of self-supervised users and fine-tuning on detailed bot detection scenarios. Extensive experiments demonstrate that SATAR outperforms competitive baselines on different bot detection datasets of varying information completeness and collection time. SATAR is also proved to generalize in real-world scenarios and adapt to evolving generations of social media bots.

Twitter has become a vital social media platform while an ample amount of malicious Twitter bots exist and induce undesirable social effects. Successful Twitter bot detection proposals are generally supervised, which rely heavily on large-scale datasets. However, existing benchmarks generally suffer from low levels of user diversity, limited user information and data scarcity. Therefore, these datasets are not sufficient to train and stably benchmark bot detection measures. To alleviate these problems, we present TwiBot-20, a massive Twitter bot detection benchmark, which contains 229,573 users, 33,488,192 tweets, 8,723,736 user property items and 455,958 follow relationships. TwiBot-20 covers diversified bots and genuine users to better represent the real-world Twittersphere. TwiBot-20 also includes three modals of user information to support both binary classification of single users and community-aware approaches. To the best of our knowledge, TwiBot-20 is the largest Twitter bot detection benchmark to date. We reproduce competitive bot detection methods and conduct a thorough evaluation on TwiBot-20 and two other public datasets. Experiment results demonstrate that existing bot detection measures fail to match their previously claimed performance on TwiBot-20, which suggests that Twitter bot detection remains a challenging task and requires further research efforts.

Linear discriminant analysis (LDA) is a popular technique to learn the most discriminative features for multi-class classification. A vast majority of existing LDA algorithms are prone to be dominated by the class with very large deviation from the others, i.e., edge class, which occurs frequently in multi-class classification. First, the existence of edge classes often makes the total mean biased in the calculation of between-class scatter matrix. Second, the exploitation of ℓ2-norm based between-class distance criterion magnifies the extremely large distance corresponding to edge class. In this regard, a novel self-weighted robust LDA with ℓ2,1-norm based pairwise between-class distance criterion, called SWRLDA, is proposed for multi-class classification especially with edge classes. SWRLDA can automatically avoid the optimal mean calculation and simultaneously learn adaptive weights for each class pair without setting any additional parameter. An efficient re-weighted algorithm is exploited to derive the global optimum of the challenging ℓ2,1-norm maximization problem. The proposed SWRLDA is easy to implement and converges fast in practice. Extensive experiments demonstrate that SWRLDA performs favorably against other compared methods on both synthetic and real-world datasets while presenting superior computational efficiency in comparison with other techniques.

Due to the expensive cost of data annotation, few-shot learning has attracted increasing research interests in recent years. Various meta-learning approaches have been proposed to tackle this problem and have become the de facto practice. However, most of the existing approaches along this line mainly focus on image and text data in the Euclidean domain. However, in many real-world scenarios, a vast amount of data can be represented as attributed networks defined in the non-Euclidean domain, and the few-shot learning studies in such structured data have largely remained nascent. Although some recent studies have tried to combine meta-learning with graph neural networks to enable few-shot learning on attributed networks, they fail to account for the unique properties of attributed networks when creating diverse tasks in the meta-training phase---the feature distributions of different tasks could be quite different as instances (i.e., nodes) do not follow the data i.i.d. assumption on attributed networks. Hence, it may inevitably result in suboptimal performance in the meta-testing phase. To tackle the aforementioned problem, we propose a novel graph meta-learning framework--Attribute Matching Meta-learning Graph Neural Networks (AMM-GNN). Specifically, the proposed AMM-GNN leverages an attribute-level attention mechanism to capture the distinct information of each task and thus learns more effective transferable knowledge for meta-learning. We conduct extensive experiments on real-world datasets under a wide range of settings and the experimental results demonstrate the effectiveness of the proposed AMM-GNN framework.

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training can still be detected. We design an end-to-end deep network based on R-C3D as the architecture for this solution. The proposed network is optimized with an innovative loss function that considers the embeddings of activity labels and their super-classes while learning the common semantics of seen and unseen activities. Experiments on both the THUMOS’14 and the Charades datasets show promising performance in terms of detecting unseen activities.

The richness in the content of various information networks such as social networks and communication networks provides the unprecedented potential for learning high-quality expressive representations without external supervision. This paper investigates how to preserve and extract the abundant information from graph-structured data into embedding space in an unsupervised manner. To this end, we propose a novel concept, Graphical Mutual Information (GMI), to measure the correlation between input graphs and high-level hidden representations. GMI generalizes the idea of conventional mutual information computations from vector space to the graph domain where measuring mutual information from two aspects of node features and topological structure is indispensable. GMI exhibits several benefits: First, it is invariant to the isomorphic transformation of input graphs—an inevitable constraint in many existing graph representation learning algorithms; Besides, it can be efficiently estimated and maximized by current mutual information estimation methods such as MINE; Finally, our theoretical analysis confirms its correctness and rationality. With the aid of GMI, we develop an unsupervised learning model trained by maximizing GMI between the input and output of a graph neural encoder. Considerable experiments on transductive as well as inductive node classification and link prediction demonstrate that our method outperforms state-of-the-art unsupervised counterparts, and even sometimes exceeds the performance of supervised ones.

Most existing object detection models are restricted to detecting objects from previously seen categories, an approach that tends to become infeasible for rare or novel concepts. Accordingly, in this paper, we explore object detection in the context of zero-shot learning, i.e., Zero-Shot Object Detection (ZSD), to concurrently recognize and localize objects from novel concepts. Existing ZSD algorithms are typically based on a simple mapping-transfer strategy that is susceptible to the domain shift problem. To resolve this problem, we propose a novel Semantics-Preserving Graph Propagation model for ZSD based on Graph Convolutional Networks (GCN). More specifically, we employ a graph construction module to flexibly build category graphs by incorporating diverse correlations between category nodes; this is followed by two semantics preserving modules that enhance both category and region representations through a multi-step graph propagation process. Compared to existing mapping-transfer based methods, both the semantic description and semantic structural knowledge exhibited in prior category graphs can be effectively leveraged to boost the generalization capability of the learned projection function via knowledge transfer, thereby providing a solution to the domain shift problem. Experiments on existing seen/unseen splits of three popular object detection datasets demonstrate that the proposed approach performs favorably against state-of-the-art ZSD methods.

Image-sentence matching is a challenging task for the heterogeneity-gap between different modalities. Ranking-based methods have achieved excellent performance in this task in past decades. Given an image query, these methods typically assume that the correct matched image-sentence pair must rank before all other mismatched ones. However, this assumption may be too strict and prone to the overfitting problem, especially when some sentences in a massive database are similar and confusable with one another. In this paper, we relax the traditional ranking loss and propose a novel deep multi-modal network with a top-k ranking loss to mitigate the data ambiguity problem. With this strategy, query results will not be penalized unless the index of ground truth is outside the range of top-k query results. Considering the non-smoothness and non-convexity of the initial top-k ranking loss, we exploit a tight convex upper bound to approximate the loss and then utilize the traditional back-propagation algorithm to optimize the deep multi-modal network. Finally, we apply the method on three benchmark datasets, namely, Flickr8k, Flickr30k, and MSCOCO. Empirical results on metrics R@K (K = 1, 5, 10) show that our method achieves comparable performance in comparison to state-of-the-art methods.

Caching contents on edge computing-enabled small cell base stations (ECSBSs) has become a promising technology for mitigating burdens of macro cell base stations and offloading data from mobile users. However, as ECSBSs may be malicious, providing a secure caching scheme becomes a challenge. In this paper, we propose a novel secure caching scheme in heterogeneous networks for multihoming users. First, to provide the cached contents, a trust mechanism is designed to verify the reliability of each ECSBS. Then, in order to guarantee the integrity of cached contents and preserve the privacy of mobile users, a Chinese remainder theorem-based privacy preservation protocol is proposed. Next, we investigate the interactions among mobile users and ECSBSs by Stackelberg game, where the trusted ECSBSs are selected to provide caching resources for mobile users with multihoming access. In addition, we analyze the Stackelberg equilibrium to jointly maximize the utilities of ECSBSs and mobile users. Extensive simulations validate the efficiency of the proposed scheme with the reliability and effectiveness to cache contents.

Semisupervised learning aims to leverage both labeled and unlabeled data to improve performance, where most of them are graph-based methods. However, the graph-based semisupervised methods are not capable for large-scale data since the computational consumption on the construction of graph Laplacian matrix is huge. On the other hand, the substantial unlabeled data in training stage of semisupervised learning could cause large uncertainties and potential threats. Therefore, it is crucial to enhance the robustness of semisupervised classification. In this paper, a novel large-scale robust semisupervised learning method is proposed in the framework of capped ℓ2,p-norm. This strategy is superior not only in computational cost because it makes the graph Laplacian matrix unnecessary, but also in robustness to outliers since the capped ℓ2,p-norm used for loss measurement. An efficient optimization algorithm is exploited to solve the nonconvex and nonsmooth challenging problem. The complexity of the proposed algorithm is analyzed and discussed in theory detailedly. Finally, extensive experiments are conducted over six benchmark data sets to demonstrate the effectiveness and superiority of the proposed method.

Tactile sensing is becoming an indispensable robotic ability for object recognition and grasping manipulation despite dealing with tactile data as the force distribution over the array sensors continuously changes as a function of time. In this paper, we propose an efficient feature extractor named linear dynamic systems based fuzzy C-means method (LDS) to encode the tactile sequences, both spatially and temporally. To this end, we decompose every input sequence into multiple subsequences, each of which is locally described by a finite-ordered observability matrix of the LDS model. A fuzzy c-means method is then applied to cluster the local LDS descriptors for learning a codebook. Conditioned on the resulting codebook, the global tactile representation is formulated by employing two different frameworks to integrate the subsequences within each tactile sequence, namely, the Vector of locally aggregated descriptor and Bag-of-Word approaches. The effectiveness of the proposed model is verified by a variety of experimental evaluations on five benchmark datasets. Results reveal that our proposed method achieves a higher classification accuracy than the state-of-the-art models with a large margin.

Spectral clustering plays a significant role in applications that rely on multi-view data due to its well-defined mathematical framework and excellent performance on arbitrarily-shaped clusters. Unfortunately, directly optimizing the spectral clustering inevitably results in an NP-hard problem due to the discrete constraints on the clustering labels. Hence, conventional approaches intuitively include a relax-and-discretize strategy to approximate the original solution. However, there are no principles in this strategy that prevent the possibility of information loss between each stage of the process. This uncertainty is aggravated when a procedure of heterogeneous features fusion has to be included in multi-view spectral clustering. In this paper, we avoid an NP-hard optimization problem and develop a general framework for multi-view discrete graph clustering by directly learning a consensus partition across multiple views, instead of using the relax-and-discretize strategy. An effective re-weighting optimization algorithm is exploited to solve the proposed challenging problem. Further, we provide a theoretical analysis of the model's convergence properties and computational complexity for the proposed algorithm. Extensive experiments on several benchmark datasets verify the effectiveness and superiority of the proposed algorithm on clustering and image segmentation tasks.

The key point of anomaly detection on attributed networks lies in the seamless integration of network structure information and attribute information. A vast majority of existing works are mainly based on the Homophily assumption that implies the nodal attribute similarity of connected nodes. Nonetheless, this assumption is untenable in practice as the existence of noisy and structurally irrelevant attributes may adversely affect the anomaly detection performance. Despite the fact that recent attempts perform subspace selection to address this issue, these algorithms treat subspace selection and anomaly detection as two separate steps which often leads to suboptimal solutions. In this paper, we investigate how to fuse attribute and network structure information more synergistically to avoid the adverse effects brought by noisy and structurally irrelevant attributes. Methodologically, we propose a novel joint framework to conduct attribute selection and anomaly detection as a whole based on CUR decomposition and residual analysis. By filtering out noisy and irrelevant node attributes, we perform anomaly detection with the remaining representative attributes. Experimental results on both synthetic and real-world datasets corroborate the effectiveness of the proposed framework.

Due to the difficulty of collecting labeled images for hundreds of thousands of visual categories, zero-shot learning, where unseen categories do not have any labeled images in training stage, has attracted more attention. In the past, many studies focused on transferring knowledge from seen to unseen categories by projecting all category labels into a semantic space. However, the label embeddings could not adequately express the semantics of categories. Furthermore, the common semantics of seen and unseen instances cannot be captured accurately because the distribution of these instances may be quite different. For these issues, we propose a novel deep semisupervised method by jointly considering the heterogeneity gap between different modalities and the correlation among unimodal instances. This method replaces the original labels with the corresponding textual descriptions to better capture the category semantics. This method also overcomes the problem of distribution difference by minimizing the maximum mean discrepancy between seen and unseen instance distributions. Extensive experimental results on two benchmark data sets, CU200-Birds and Oxford Flowers-102, indicate that our method achieves significant improvements over previous methods.

Video semantic recognition usually suffers from the curse of dimensionality and the absence of enough high-quality labeled instances, thus semisupervised feature selection gains increasing attentions for its efficiency and comprehensibility. Most of the previous methods assume that videos with close distance (neighbors) have similar labels and characterize the intrinsic local structure through a predetermined graph of both labeled and unlabeled data. However, besides the parameter tuning problem underlying the construction of the graph, the affinity measurement in the original feature space usually suffers from the curse of dimensionality. Additionally, the predetermined graph separates itself from the procedure of feature selection, which might lead to downgraded performance for video semantic recognition. In this paper, we exploit a novel semisupervised feature selection method from a new perspective. The primary assumption underlying our model is that the instances with similar labels should have a larger probability of being neighbors. Instead of using a predetermined similarity graph, we incorporate the exploration of the local structure into the procedure of joint feature selection so as to learn the optimal graph simultaneously. Moreover, an adaptive loss function is exploited to measure the label fitness, which significantly enhances model's robustness to videos with a small or substantial loss. We propose an efficient alternating optimization algorithm to solve the proposed challenging problem, together with analyses on its convergence and computational complexity in theory. Finally, extensive experimental results on benchmark datasets illustrate the effectiveness and superiority of the proposed approach on video semantic recognition related tasks.

To save energy during content delivery in green cities, caching contents on edge nodes that are placed near mobile social users has been advocated recently. However, how to allocate the limited caching resources with secure content delivery becomes a new challenge. Therefore, in this paper, we present a novel theoretical model to deliver secure content with edge nodes in order to save energy for green cities. First, we present a reverse auction game to encourage edge nodes to cooperatively provide caching services with incentives. With the model, mobile users can determine the candidate of edge node to cache content based on the interaction between mobile users and edge nodes. Second, a trust management method is designed to evaluate the reliability of the selected candidate of edge node by considering the direct trust evaluation. Finally, extensive simulations show that the proposal can save energy with a secure content delivery where both the delay to obtain the content and the caching ratio can be improved compared with the conventional methods.

Feature selection is one of the most important dimension reduction techniques for its efficiency and interpretation. Since practical data in large scale are usually collected without labels, and labeling these data are dramatically expensive and time-consuming, unsupervised feature selection has become a ubiquitous and challenging problem. Without label information, the fundamental problem of unsupervised feature selection lies in how to characterize the geometry structure of original feature space and produce a faithful feature subset, which preserves the intrinsic structure accurately. In this paper, we characterize the intrinsic local structure by an adaptive reconstruction graph and simultaneously consider its multiconnected-components (multicluster) structure by imposing a rank constraint on the corresponding Laplacian matrix. To achieve a desirable feature subset, we learn the optimal reconstruction graph and selective matrix simultaneously, instead of using a predetermined graph. We exploit an efficient alternative optimization algorithm to solve the proposed challenging problem, together with the theoretical analyses on its convergence and computational complexity. Finally, extensive experiments on clustering task are conducted over several benchmark data sets to verify the effectiveness and superiority of the proposed unsupervised feature selection algorithm.

Traditional topic model with maximum likelihood estimate inevitably suffers from the conditional independence of words given the document’s topic distribution. In this paper, we follow the generative procedure of topic model and learn the topic-word distribution and topics distribution via directly approximating the word-document co-occurrence matrix with matrix decomposition technique. These methods include: (1) Approximating the normalized document-word conditional distribution with the documents probability matrix and words probability matrix based on probabilistic non-negative matrix factorization (NMF); (2) Since the standard NMF is well known to be non-robust to noises and outliers, we extended the probabilistic NMF of the topic model to its robust versions using l21-norm and capped l21-norm based loss functions, respectively. The proposed framework inherits the explicit probabilistic meaning of factors in topic models and simultaneously makes the conditional independence assumption on words unnecessary. Straightforward and efficient algorithms are exploited to solve the corresponding non-smooth and non-convex problems. Experimental results over several benchmark datasets illustrate the effectiveness and superiority of the proposed methods.

The lack of labeled exemplars is an important factor that makes the task of multimedia event detection (MED) complicated and challenging. Utilizing artificially picked and labeled external sources is an effective way to enhance the performance of MED. However, building these data usually requires professional human annotators, and the procedure is too time-consuming and costly to scale. In this paper, we propose a new robust dictionary learning framework for complex event detection, which is able to handle both labeled and easy-to-get unlabeled web videos by sharing the same dictionary. By employing the lq-norm based loss jointly with the structured sparsity based regularization, our model shows strong robustness against the substantial noisy and outlier videos from open source. We exploit an effective optimization algorithm to solve the proposed highly non-smooth and non-convex problem. Extensive experiment results over standard datasets of TRECVID MEDTest 2013 and TRECVID MEDTest 2014 demonstrate the effectiveness and superiority of the proposed framework on complex event detection.

Semi-supervised learning plays a significant role in multi-class classification, where a small number of labeled data are more deterministic while substantial unlabeled data might cause large uncertainties and potential threats. In this paper, we distinguish the label fitting of labeled and unlabeled training data through a probabilistic vector with an adaptive parameter, which always ensures the significant importance of labeled data and characterizes the contribution of unlabeled instance according to its uncertainty. Instead of using traditional least squares regression (LSR) for classification, we develop a new discriminative LSR by equipping each label with an adjustment vector. This strategy avoids incorrect penalization on samples that are far away from the boundary and simultaneously facilitates multi-class classification by enlarging the geometrical distance of instances belonging to different classes. An efficient alternative algorithm is exploited to solve the proposed model with closed form solution for each updating rule. We also analyze the convergence and complexity of the proposed algorithm theoretically. Experimental results on several benchmark datasets demonstrate the effectiveness and superiority of the proposed model for multi-class classification tasks.

Robust principal component analysis (PCA) is one of the most important dimension-reduction techniques for handling high-dimensional data with outliers. However, most of the existing robust PCA presupposes that the mean of the data is zero and incorrectly utilizes the average of data as the optimal mean of robust PCA. In fact, this assumption holds only for the squared [Formula: see text]-norm-based traditional PCA. In this letter, we equivalently reformulate the objective of conventional PCA and learn the optimal projection directions by maximizing the sum of projected difference between each pair of instances based on [Formula: see text]-norm. The proposed method is robust to outliers and also invariant to rotation. More important, the reformulated objective not only automatically avoids the calculation of optimal mean and makes the assumption of centered data unnecessary, but also theoretically connects to the minimization of reconstruction error. To solve the proposed nonsmooth problem, we exploit an efficient optimization algorithm to soften the contributions from outliers by reweighting each data point iteratively. We theoretically analyze the convergence and computational complexity of the proposed algorithm. Extensive experimental results on several benchmark data sets illustrate the effectiveness and superiority of the proposed method.

Linguistic pairwise comparison matrices are widely used in decision-making procedures. However, the matrices often give conflicting results when there are multiple criteria under consideration. Despite intensive research, achieving consistency of such matrices remains a daunting task. In this paper, a novel approach based on linguistic discrete region is proposed to address the challenge. Unlike existing methods that require a single value for each comparison, our approach allows a comparison to be expressed by a discrete region with multiple linguistic terms. Such front-end gives users more freedom to express their opinions. In the back-end, we propose an iterative searching algorithm that is able to achieve approximate optimal consistency for the comparison matrices with discrete region values. The final results are single-value matrices that not only guarantee approximate optimal consistency but comply with evaluators' intentions a well, as our approach does not modify any linguistic values like many existing methods. We have conducted extensive evaluations, and our empirical study confirms that the linguistic discrete region-based approach significantly improves the consistency of linguistic pairwise comparison matrices.

In this paper, the objective function of fuzzy c-regression models (FCRM) is modified to develop a novel fuzzy partition method on the basis of block structured sparse representation, namely as sparse fuzzy c-regression model. This method takes advantage of the block structured information in the objective function of FCRM and casts fuzzy partition into an optimization problem by making a tradeoff between traditional FCRM and the number of prototypes of hyper-plane with nonzero parameters. An alternating direction method of multipliers (ADMM) based algorithm is exploited to address the proposed optimization problem. Furthermore, based on sparse fuzzy c-regression models, a novel T-S fuzzy systems identification method is developed for reduction of fuzzy rules. Finally, examples on well-known benchmark data set are carried out to illustrate the effectiveness of the proposed methods.

Takagi–Sugeno (T–S) fuzzy system identification provides a reasonable framework for modeling and approximation by decomposition of a nonlinear system into a collection of local linear models. In this paper, we extend the multidimensional output fuzzy rule from the corresponding single-output fuzzy rule with the important difference in the variable definition of output, namely the output of each fuzzy rule is represented by a multidimensional vector instead of a scalar value. In this case, the consequent of the fuzzy rule with the multidimensional output variable share a common antecedent part. Different from the traditional methods that separate the multi-input–multi-output fuzzy system into a group of multi-input-single-output fuzzy models, in this paper, we take into account the block structure information in the T–S fuzzy system and cast the problem of multidimensional output fuzzy model identification as a joint structure sparse optimization problem, where the consequent parameters are estimated with a common block structured sparsity pattern over all dimensions of the output variable. Furthermore, we exploit a joint block sparse orthogonal-match-pursuit algorithm to reduce the number of fuzzy rules in terms of all dimensions of the output variable and prove the sufficient conditions in consideration of the multidimensional output together with the block structure in the T–S fuzzy model. This method is efficient and shows good performance in well-known benchmark datasets and real-world problems.

“The curse of dimensionality” has become a significant bottleneck for fuzzy system identification and approximation. In this paper, we cast the Takagi–Sugeno (T–S) fuzzy system identification into a hierarchical sparse representation problem, where our goal is to establish a T–S fuzzy system with a minimal number of fuzzy rules, which simultaneously have a minimal number of nonzero consequent parameters. The proposed method, which is called hierarchical sparse fuzzy inference systems ( H-sparseFIS), explicitly takes into account the block-structured information that exists in the T–S fuzzy model and works in an intuitive way: First, initial fuzzy rule antecedent part is extracted automatically by an iterative vector quantization clustering method; then, with block-structured sparse representation, the main important fuzzy rules are selected, and the redundant ones are eliminated for better model accuracy and generalization performance; moreover, we simplify the selected fuzzy rules consequent with sparse regularization such that more consequent parameters can approximate to zero. This algorithm is very efficient and shows good performance in well-known benchmark datasets and real-world problems.

In this paper, necessary conditions are investigated for a single input/single output (SISO) Mamdani fuzzy systems as function approximators of continuous functions within a given accuracy. Since general SISO Mamdani fuzzy systems are monotonic on subintervals, the optimal configuration of fuzzy systems is that the number of division points is at least the times of its monotonicity changes. Thus with the extreme of the desired continuous function, necessary conditions are obtained through generating intervals that contain division points and pruning redundant intervals. Furthermore, a dynamically constructive method is proposed to show the conditions are optimal. It has been shown that existing results concerning necessary conditions are only special cases of our results. Finally, simulation examples are given to illustrate the conclusions, the strength of the fuzzy systems as function approximators are analyzed.