Temporal knowledge graph reasoning (TKGR) excels at inferring missing event‐centric facts within a timeline, thereby mitigating the inherent incompleteness of real‐world data. Existing TKGR methods predominantly exploit intrasnapshot structural patterns and intersnapshot temporal dependencies. However, they often fail to incorporate valuable time‐invariant factual knowledge about events and struggle to jointly model entity–relation evolution dynamics. To address these challenges, we propose CKE 3 , a novel contrastive knowledge‐enhanced event evolution model that integrates time‐invariant entity background knowledge with time‐variant structural information for enhanced reasoning. Specifically, CKE 3 improves the learning of expressive entity and relation representations through an adaptive knowledge retrieval strategy, which constructs descriptive common sense knowledge associated with each entity to provide richer contextual information. Moreover, we introduce a knowledge‐aware hierarchical structural–temporal modeling module that jointly captures entity–relation structural interactions as well as sequential and periodic temporal patterns across knowledge graph snapshots. To further mitigate the impact of knowledge noise, we design a self‐supervised augmentation task that promotes the fusion of relevant information while alleviating noise. Extensive experiments on four public TKGR datasets demonstrate that CKE 3 consistently surpasses state‐of‐the‐art baselines, highlighting its effectiveness in accurate entity forecasting for the TKGR task.

Micro-video popularity prediction (MVPP) plays a crucial role in numerous real-world applications, including product marketing and recommendation systems. While existing methodologies predominantly assume complete modalities during multimodal learning, this assumption often fails to hold in practical scenarios due to various constraints, such as privacy concerns or data integrity issues. To address this limitation, we propose SCRAG, a novel Self-Correlation Retrieval-Augmented Generative framework designed to enhance missing-modality robustness in MVPP. SCRAG operates in a retrieval-guided generation manner that explores relevant knowledge to enhance the reconstruction of missing content, which consists of two primary components: (1) a self-correlation retriever and (2) a multimodal mixture-of-experts generator. It first acquires instances pertinent to the missing content through multimodal prompt alignment. Subsequently, the generator extracts contextual modal information from the retrieved context-rich instances. By learning the joint distribution of modalities, SCRAG effectively recovers missing content and addresses the modal heterogeneity challenge inherent in cross-modal generation approaches. Extensive experiments conducted on three real-world datasets demonstrate that SCRAG consistently outperforms state-of-the-art baselines, underscoring its effectiveness in handling incomplete modalities and improving the accuracy of micro-video popularity prediction.

Zero-shot composed image retrieval (ZS-CIR) is a challenging task that aims to retrieve images similar to a composed query of a reference image and a description, without relying on training on triplet datasets. Existing methods for this task often rely on predefined, fixed retrieval processes that combine the image and the modified text through hand-crafted templates, which suffer from two main issues: non-adaptive retrieval queries and user-unfriendly retrieval processes. To address these limitations, we propose a novel framework - Automatic Multi-Agent Collaboration for Zero-Shot Composed Image Retrieval (AutoCIR). AutoCIR consists of three training-free agents - a planner, a retriever, and a corrector - that work together to iteratively identify and rectify mismatches. The planner guides the retriever by generating a customized target caption for the composed query and further refines this caption to resolve any semantic discrepancies based on feedback. The corrector, equipped with a chain-of-thought reasoning mechanism, conducts an in-depth evaluation of the retrieved results and generates appropriate self-correction actions. Extensive experiments on three benchmarks demonstrate that AutoCIR consistently outperforms previous competitive methods for ZS-CIR.

Traditional multimodal learning approaches often assume that all modalities are available during both the training and inference phases. However, this assumption is often impractical in real-world scenarios due to challenges such as sensor failures, data corruption, or privacy concerns. While recent efforts focus on enhancing the robustness of pre-trained Multimodal Transformers (MTs) under missing modality conditions, mainstream work in this field often overlook reconstructing the missing modalities and rely on static, sample-agnostic prompt-tuning techniques, undermining their efficacy in severe modality missing scenarios. To address these limitations, we propose REDEEM, a novel REtrieval-guiDEd conditional gEnerative fraMework that largely alleviates the modality missing problems on pre-trained MTs. REDEEM consists of a new adaptive retrieval mechanism to identify relevant instances for both modality-complete and -incomplete samples. It then conditions on the remaining modalities and utilizes the retrieved data as experts to effectively recover the missing ones in modality-incomplete instances through a within-modal reconstruction manner. Finally, REDEEM generates sample-aware inter-modal prompts from the retrieved instances to guide MTs in tackling severe modality missing challenges. Comprehensive experiments on three diverse multimodal classification benchmarks demonstrate that REDEEM significantly outperforms competitive baselines.

Micro-video popularity prediction (MVPP) is a crucial research topic with important implications for social media marketing and stakeholders. Current works in MVPP utilized the pre-trained vision-language models (PVLs) to model the multimodal features for prediction, failing to capture the evolving popularity trend in micro-videos and leading to suboptimal results. To tackle this limitation, we propose EvoPro, an Evolution-aware Prompt-augmented framework that enhances MVPP. First, inspired by the powerful multimodal understanding and text generation skills of Large Multimodal Models (LMMs), an LMM-driven generative retriever is proposed to create contextually rich retrieval queries and perform precise video-to-video retrieval, forming dynamic micro-video support sets that effectively reflect evolving patterns. Building upon this, a graph-based prompter generates evolutionary prompts by capturing the relational structures within the support set. These prompts, representing the latest trend dynamics, serve as few-shot examples to guide PVLs. By integrating evolutionary prompts, the PVLs are empowered to model the evolving popularity trends more accurately, yielding stronger and more predictive representations. Extensive experiments conducted on three benchmarks demonstrate that EvoPro significantly outperforms competitive baselines.

The rapid spread of rumor content on online micro-video platforms poses significant threats to public health and safety. However, existing Micro-Video Rumor Detection (MVRD) methods are generally black-box, which lacks transparency and makes it difficult to understand the reasoning behind classification decisions. In this work, we introduce ExMRD, a novel Explainable Micro-video Rumor Detection framework designed to generate detailed and coherent explanations for enhancing MVRD. Inspired by the powerful reasoning capacity of Chain-of-Thought (CoT), we introduce a novel inference mechanism called R3CoT-- consisting of Refining, Retrieving, and Reasoning on MVRD. This mechanism enables Multimodal Large Language Models (MLLMs) to reorganize the original video content, retrieve domain knowledge related to rumors, and generate explainable conclusions regarding whether the micro-video contains rumor information. Instead of directly fine-tuning MLLMs for MVRD, which is computationally expensive, we propose a Small Language Reviewer (SLReviewer), which distills the outputs of R3CoT guided MLLMs to ensure efficient and reliable predictions. Extensive experiments on three real-world benchmarks demonstrate that ExMRD significantly outperforms competitive baselines while providing high-quality rationales.

Information diffusion prediction is a vital component for a wide range of social applications, including viral marketing identification and precise recommendation. Prior methods focus on modeling contextual information from a single cascade, ignoring rich collaborative information behind historical interactions across various cascades and future data within the cascade. Leveraging such interactions can substantially enhance diffusion prediction performance but presents two major challenges: (1) user intents are usually entangled behind historical interactions; and (2) utilizing future data may introduce severe training-inference discrepancies. We present MIM, a novel information diffusion model merging multi-scale interactions for improving user intent learning and behavior retrieval. Specifically, we convert cascades and social relations into multi-channel hypergraphs, where each channel depicts a common fine-grained user intent behind historical interactions across cascades. By aggregating embeddings learned through multiple channels, we obtain comprehensive intent representations. Second, we decouple past- and future-level temporal influences within a cascade via a dual temporal network. Then we implement past-future knowledge transferring to enhance the knowledge learnt from the dual network via hierarchical knowledge distillation. Extensive experiments conducted on four datasets demonstrate that MIM significantly outperforms various benchmarks.

Accurately predicting the popularity of multimodal user-generated content (UGC) is fundamental for many real-world applications such as online advertising and recommendation. Existing approaches generally focus on limited contextual information within individual UGCs, yet overlook the potential benefit of exploiting meaningful knowledge in relevant UGCs. In this work, we propose RAGTrans, an aspect-aware retrieval-augmented multi-modal hypergraph transformer that retrieves pertinent knowledge from a multi-modal memory bank and enhances UGC representations via neighborhood knowledge aggregation on multi-model hypergraphs. In particular, we initially retrieve relevant multimedia instances from a large corpus of UGCs via the aspect information and construct a knowledge-enhanced hypergraph based on retrieved relevant instances. This allows capturing meaningful contextual information across the data. We then design a novel bootstrapping hypergraph transformer on multimodal hypergraphs to strengthen UGC representations across modalities via customizing a propagation algorithm to effectively diffuse information across nodes and edges. Additionally, we propose a user-aware attention-based fusion module to comprise the enriched UGC representations for popularity prediction. Extensive experiments on real-world social media datasets demonstrate that RAGTrans outperforms state-of-the-art popularity prediction models across settings.

Accurately predicting the popularity of micro-videos is crucial for real-world applications such as recommender systems and identifying viral marketing opportunities. Existing methods often focus on limited cross-modal information within individual micro-videos, overlooking the potential advantages of exploiting vast repository of past videos. We present MMRA, a multi-modal retrieval-augmented popularity prediction model that enhances prediction accuracy using relevant retrieved information. MMRA first retrieves relevant instances from a multi-modal memory bank, aligning video and text through transformation mechanisms involving a vision model and a text-based retriever. Additionally, a multi-modal interaction network is carefully designed to jointly capture cross-modal correlations within the target video and extract informative knowledge through retrieved instances, ultimately enhancing the prediction. Extensive experiments conducted on the real-world micro-video dataset demonstrate the superiority of MMRA when compared to state-of-the-art models. The code and data are available at https://github.com/ICDM-UESTC/MMRA.

Information diffusion prediction, which aims to infer the infected behavior of individual users during information spread, is critical for understanding the dynamics of information propagation and users' influence on online social media. To date, existing methods either focus on capturing limited contextual information from a single cascade, overlooking the potentially complex dependencies across different cascades, or they are committed to improving model performance by using intricate technologies to extract additional features as supplements to user representations, neglecting the drift of model performance across different platforms. To address these limitations, we propose a novel framework called CARE (CAscade-REtrieved In-Context Learning) inspired by the concept of in-context learning in LLMs. Specifically, CARE first constructs a prompts pool derived from historical cascades, then utilizes ranking-based search engine techniques to retrieve prompts with similar patterns based on the query. Moreover, CARE also introduces two augmentation strategies alongside social relationship enhancement to enrich the input context. Finally, the transformed query-cascade representation from a GPT-type architecture is projected to obtain the prediction. Experiments on real-world datasets from various platforms show that CARE outperforms state-of-the-art baselines in terms of effectiveness and robustness in information diffusion prediction.

Information cascade popularity prediction is an important problem in social network content diffusion analysis. Various facets have been investigated (e.g., diffusion structures and patterns, user influence) and, recently, deep learning models based on sequential architecture and graph neural network (GNN) have been leveraged. However, despite the improvements attained in predicting the future popularity, these methodologies fail to capture two essential aspects inherent to information diffusion: (1) the temporal irregularity of cascade event – i.e., users’ re-tweetings at random and non-periodic time instants; and (2) the inherent uncertainty of the information diffusion. To address these challenges, in this work, we present CasDO – a novel framework for information cascade popularity prediction with probabilistic diffusion models and neural ordinary differential equations (ODEs). We devise a temporal ODE network to generalize the discrete state transitions in RNNs to continuous-time dynamics. CasDO introduces a probabilistic diffusion model to consider the uncertainties in information diffusion by injecting noises in the forwarding process and reconstructing cascade embedding in the reversing process. Extensive experiments that we conducted on three large-scale datasets demonstrate the advantages of the CasDO model over baselines.

Accurately predicting information diffusion is critical for a vast range of applications. Existing methods generally consider user re-sharing behaviors to be driven by a single intent, and/or assume cascade temporal influence to be unchanged, which might not be consistent with real-world scenarios. To address these issues, we propose a self-supervised disentanglement framework (DisenIDP) for information diffusion prediction. First, we construct intent-aware hypergraphs to capture users' potential intents from different perspectives, and then perform the light hypergraph convolution to adaptively activate disentangled intents. Second, we extract long-term and short-term cascade influence via independent attention-based encoders. Finally, we set a self-supervised disentanglement task to alleviate the information loss and learn better-disentanglement representations. Extensive experiments conducted on two real-world social datasets demonstrate that DisenIDP outperforms state-of-the-art models across several settings.

The exponential growth of digital information has amplified the necessity for effective rumor detection on social media. However, existing approaches often neglect the inherent noise and uncertainty in rumor propagation, leading to obscure learning mechanisms. Moreover, current deep-learning methodologies, despite their top-tier performance, are heavily dependent on supervised learning, which is labor-intensive and inefficient. Their prediction credibility is also questionable. To tackle these issues, we present a new framework, TrustRD, for reliable rumor detection. Our framework incorporates a self-supervised learning module, designed to derive interpretable and informative representations with less reliance on large labeled data sets. A downstream model based on Bayesian networks, which is further refined with adversarial training, enhances performance while providing a quantifiable trustworthiness assessment of results. Our methods' effectiveness is confirmed through experiments on two benchmark datasets.