Assessing enterprise resilience under uncertainty necessitates capturing both intrinsic attributes and evolving inter-enterprise dependencies. However, real-world enterprise systems pose substantial structural challenges: redundant or loosely correlated links can trigger spurious relational inferences, while missing or latent dependencies often hinder the propagation of informative signals. Moreover, most existing approaches adopt static graph priors or decouple structural refinement from semantic learning, lacking a co-evolutionary paradigm that allows structure and representation to inform one another. We propose CFU, a novel Co-evolving Framework under Uncertainty, which reconceptualizes graph structure as a dynamic and learnable component evolving alongside node semantics. Specifically, CFU begins with a structure-aware contrastive pretraining phase to distill latent relational semantics without supervision. It then performs bidirectional structural refinement, filtering structurally redundant edges through semantic agreement scoring, and uncovering temporally contingent, task-relevant dependencies via similarity-guided inference. These operations are integrated through a dynamic fusion procedure that continuously aligns the evolving topology with the resilience objective. By embedding structural adaptation within the learning loop, CFU enables context-aware resilience assessment across incomplete, ambiguous, and structurally volatile enterprise environments. Ultimately, extensive experiments conducted on real-world datasets demonstrate its superior performance across diverse evaluation scenarios.

The rise of location-sharing applications (LSA) marks a significant convergence between social networks and Geographic Information Systems (GIS). With a large number of users, LSAs generate vast amounts of location-sharing data every day. Analyzing these data can enhance our understanding of human mobility behavior and drive the development of various mobility-aware downstream tasks. However, due to the unintentional acts driven by personal fuzzy check-ins and the attraction incentives intentionally offered by LSAs, location-sharing data often exhibits uncertainties, i.e., (purposely) fake shares exist in user trajectories, further affecting reliability/authenticity. Thus, inferring the real location shares in a user's trajectory becomes an urgent task. In this study, we formalize this challenge as Authentic Location-Share Alignment (AuLA) and correspondingly propose the AuLAB solution to address it. Specifically, AuLAB is built upon a newly derived Mobility Information Bottleneck (MIB) mechanism, grounded in Information Bottleneck (IB) theory, to enhance mobility representation learning for aligning authentic shares. It also introduces context-aware attention to capture global and local dependencies among location shares, ensuring a comprehensive understanding of interactive dynamics. Experiments on four real-world datasets demonstrate the superiority of our proposed AuLAB over existing methods.

Trajectory recovery (TrajRec), which primarily seeks to reconstruct complete trajectories from segments sampled at low rates and align them with road networks, has gained attention in both urban computing and intelligent transportation areas. Existing solutions predominantly focus on using dependency learning to bridge the gap between the missing and the observed parts constrained by the road network–while rarely considering the positive signals of spatiotemporal corrections in a self-augmenting manner and ignoring transition pReferences alongside road network limitations. To this end, this study proposes a novel road-informed solution that combinesDual-offset trajectory learning with dynamicTransitionProbability (DTPTrajRec), primarily striving to enhance inherent spatiotemporal correlations with dual-offset trajectories while aligning the inferred GPS points with roads by collaborating them with dynamic transition preferences. More importantly, our proposed DTPTrajRec concentrates on enhancing the low-quality trajectory data by filling gaps (missing points) with the nearest available points and managing them within latent spaces, yielding more robust trajectory representations. To improve recovery reliability, it synchronizes transition preferences with road restrictions using adaptive transition probabilities. In the end, experimental results on two large-scale taxi datasets demonstrate the superiority of our DTPTrajRec over several baseline methods.

The inherent fluctuations in the stock market present significant challenges in understanding stock dynamics, especially for investment decisions based on stock ranking. Recent advancements in learning-based methods have led to promising results in exploring temporal dependencies to understand stock movements. However, they often assume stable, certain, and reliable environments, narrowing their insight into the complex and fluctuating nature of markets. This complexity is driven by two influential factors: the explicit consistency of dynamic yet stable trends across diverse temporal patterns, coupled with the implicit interplay of logic and possibility under uncertainty. Hence, we introduce aSensitivity-awareDependencyLearning solution (SDL) for stock ranking. With bridging the ideal and reality in mind, SDL captures short-term fluctuations under the guidance of long-term dependencies, associated with the augmentation of counterfactual knowledge. Specifically, SDL devises aShort-termCo-integrationDetector (SCD) that concentrates on capturing time-varying correlations and immediate market reactions, in addition to multi-period attention. Furthermore, aLong-termCo-movementsTracker (LCT) takes advantage of enduring industry relationships and incorporates counterfactual knowledge, allowing the model to generalize beyond observed patterns and identify diverse long-term trends. Comprehensive experiments on five real-world stock markets demonstrate that our proposed SDL outperforms several representative baselines.

The metro flow in Urban Rail Transit Systems (URTS) differs from other urban traffic flows because it is characterized by: (1) highly predetermined scheduling; and (2) interactively dynamic dependencies over the fixed physical infrastructure that vary with spatiotemporal and environmental factors. Notwithstanding the advances in graph neural networks, existing efforts fail to fully capture the characteristics and complex spatiotemporal dynamics specific to metro flow, as the innate graph-aware interactions underlying a metro flow are frequently affected by an amalgamation of: intrinsic connectivity, environmental associations, and flow-activated correlation, which usually dynamically evolve over time while containing redundant signals. We propose ReDyNet, a novel Responsive Dynamic Graph Neural Network to accurately understand the spatiotemporal dynamics of metro flow and external factors. Specifically, it employs a responsive mechanism that adapts to variations in metro flow and external influences, ensuring the construction of an appropriate dynamic graph. In addition, ReDyNet follows the merits of information bottleneck (IB) theory with redundancy disentanglement to enhance the clarity and precision of contextual spatial signals. Our experiments conducted on three real-world metro passenger flow datasets demonstrate that the proposed ReDyNet outperforms several representative baselines.

Few-shot Named Entity Recognition (NER) spotlights the tag of novel entity types in data-limited scenarios or lower-resource settings. Advances with Pre-trained Language Models (PLMs), including BERT, GPT, and their variants, have driven tremendous strategies to leverage context-dependent representations and exploit predefined relational cues, yielding significant gains in witnessing unseen entities. Nevertheless, a fundamental issue exists in prior efforts regarding their susceptibility to adversarial attacks in the intricate semantic environment. This vulnerability undermines the robustness of semantic representations, exacerbating the challenge of accurate entity identification, especially when transitioning across domains. To this end, we propose an Adversity-aware Augment Learning (AAL) solution for the few-shot NER task, dedicated to retrieving and reinforcing entity prototypes resilient to adversarial inference, thereby enhancing cross-domain semantic coherence. In particular, AAL employs a two-stage paradigm consisting of training and fine-tuning. The process initiates with augmentation learning by leveraging two kinds of prompt learning schemes, then identifies prototypes under the guidance of a variational manner. Furthermore, we devise a domain-oriented prototype refinement to optimize prototype learning under conditions of uncertainty attack, facilitating the effective transfer of common knowledge from source to target domains. The experimental results, encompassing the few-shot NER datasets under both certainty and uncertainty conditions, affirm the superiority of the proposed AAL over several representative baselines, particularly its capability against adversarial attacks.

High-quality embeddings for urban regions have enabled influential insights into urban structures and characteristics, facilitating the creation of more sustainable cities. However, the existing practices still face certain challenges, notably: (1) When multiple views contain distinct semantic information, ignoring the reliability and possibly inadequate collection differences (e.g., data missingness) among those views may degrade the representation robustness. (2) Consensus semantics extracted from different views are often fused in a simplistic manner, without considering the uniformity of embeddings (quality variations) and the complementarity between views. To address such challenges, we propose a novel Adaptive Risk-aware Consensus learning (ARC) solution for urban region embeddings. Specifically, we design both local- and region-level masking within the inter-view representation, following the paradigm of masked autoencoders, to better handle uncertainty risks. More importantly, we introduce a self-weighted contrastive mechanism in consensus learning to achieve maximum alignment and mitigate degradation. To enhance the uniformity of embeddings, we employ entropy, ensuring the diversity and complementarity of information. Ultimately, we apply the learned embeddings to down-stream tasks, demonstrating remarkable improvements compared to several representative baselines.

The automatic and accurate detection of online fake news is crucial to society, drawing significant attention from both industry and academia. With news content becoming increasingly multimodal, assessing its truthfulness has become more challenging. Existing efforts to combat multimodal fake news primarily follow a target-egocentric paradigm, which makes predictions based solely on features extracted from the target news and its associated social context. However, their performance is constrained by the inherent knowledge paucity within the target news. To address this challenge, we propose ReTIP, a novel retrieval-enhanced framework for multimodal fake news detection. ReTIP enriches the knowledge of target news by retrieving relevant news content, along with potential diffusion participants. Specifically, ReTIP retrieves relevant content from a local content pool using a key vector generated through the joint modeling of text and images, and employs a communitybased strategy to retrieve potential participants from a historical user interaction pool. Additionally, ReTIP employs a hypergraphbased information enhancement module to align knowledge across modalities and instances at a fine-grained level by capturing higher-order correlations. Finally, an attention-based fusion layer is employed to aggregate the multi-element knowledge from retrieved instances, which is then concatenated with the target news knowledge for the final prediction. Extensive experiments on three real-world multimodal fake news datasets not only demonstrate the superior performance of ReTIP compared to state-of-the-art baselines but also confirm the effectiveness of its individual components. Our code is made publicly available at https://github.com/xytitor/ReTIP.

Recently, the fully-connected tensor network (FCTN) decomposition has shown a powerful capability of depicting intrinsic correlations between any pair of tensor modes. But there exists a challenging question in FCTN decomposition-based methods, i.e., the accurate determination of the complicated FCTN-rank, which contains${N(N-1)}/{2}$elements for$N$th-order tensors. In this paper, we design a structural sparsity regularization for the FCTN decomposition, which estimates the complicated FCTN-rank by adaptively pruning near-zero groups in FCTN factor. Based on this regularization, we propose a noisy tensor completion (NTC) model, aiming at the recovery of a tensor from its partial and noisy observation. Besides, we design a proximal alternating minimization (PAM)-based algorithm to solve the model. In theorem, we prove a guarantee for the global convergence of the developed algorithm. To further accelerate our method for large-scale data sets, we customize the randomized block sampling strategy for general tensor network decomposition methods by updating factors from small samples. Experiments demonstrate that our strategy can accurately estimate the FCTN-rank and achieve better reconstruction performances, and our methods outperform the state-of-the-art methods in the reconstruction of different types of real-world tensors.

Optimizing stock selection through stock ranking is one of the critical but intricate tasks in quantitative trading areas because of the non-stationary dynamics and complicated interdependencies behind stock markets. Recent studies have made efforts to model historical market movements to enhance stock selection. However, they primarily borrowed the spirit of time series modeling and sought to build a deterministic paradigm without considering the uncertain fluctuations. In addition, some of these studies tailor to explore stock correlations from a predefined (e.g., binary) graph structure and use explicitly simple relations (such as first-order relations) to guide evolving interactions. Nevertheless, aggregating predefined but shallow relationships to collaborate with stock movements may affect selection generalizability and increase the risk of portfolio failure. This study introduces a novelRelational stock selection framework via probabilisticStateSpaceLearning (orRSSL) for stock selection. Specifically, RSSL first attempts to build a tree-based structure to explicitly expose higher-order relations in the stock market, primarily by discovering a hierarchical delineation of ties between stocks. Whereafter, it couples with time-varying movements via an attention mechanism to smoothly explore the interactive correlations among different stocks. Inspired by recent state space models (SSM) in probabilistic Bayesian learning, we devise a Probabilistic Kalman Network (PKNet) with uncertainty estimates to recursively simulate ever-changing stock volatility, enabling more promising return-risk trade-offs. The experimental results on several real-world stock market datasets demonstrate that RSSL outperforms several representative baseline methods by a significant margin.

Event Causality Identification (ECI) focuses on extracting causal relations between events in texts.Existing methods for ECI primarily rely on causal features and external knowledge.However, these approaches fall short in two dimensions: (1) causal features between events in a text often lack explicit clues, and (2) external knowledge may introduce bias, while specific problems require tailored analyses.To address these issues, we propose SemDI -a simple and effective Semantic Dependency Inquiry Network for ECI.SemDI captures semantic dependencies within the context using a unified encoder.Then, it utilizes a Cloze Analyzer to generate a fill-in token based on comprehensive context understanding.Finally, this fill-in token is used to inquire about the causal relation between two events.Extensive experiments demonstrate the effectiveness of SemDI, surpassing state-of-the-art methods on three widely used benchmarks.Code is available at https://github.com/hrlics/SemDI.

Graph neural networks, as well as attention mechanisms, have gained widespread popularity for traffic flow forecasting due to their capacity to incorporate the complicated interactions behind flow dynamics. However, existing solutions either formulate a graph-based skeleton with narrow (e.g., static) interaction capture or build the spatiotemporal (e.g., dynamic) attention without proper comprehension of diverse risks, which inevitably burdens the generalization of high-accuracy traffic trends. In this study, we introduce Gboot (Graph bootstrap) enhancement framework for traffic flow forecasting. Gboot takes the traffic flow forecasting problem from a dependency dynamic learning perspective by treating each traffic sensor as the graph node while regarding the observed flows at each sensor as the node feature. In addition to exposing the explicit spatial connectivity behind traffic flows, we hierarchically devise temporal-aware and factual-aware graph learning blocks to consider temporal interactive dynamics and factual interactive dynamics. The former shows the trend dependencies behind flow signals and the latter uncovers different views of traffic situations (e.g., current observation vs. historical observation). More importantly, we present a Dual-view Bootstrap (DvBoot) mechanism in Gboot, which includes both risk-free and risk-aware stands. DvBoot attempts to flexibly align these two views in the latent space to enhance the generalization capability of capturing dynamic dependencies. Experiments on several real-world traffic datasets demonstrate the superiority of our Gboot over representative approaches.

Text summarization is to generate a brief version of a given article while maintaining its essential meaning. Most existing solutions typically relied on the standard attention-based encoder-decoder framework, where each token in the source article, including redundancy, would be contributed to the de-coder through the attention mechanism. It follows that how to filter out the redundant content becomes an important issue in the text summarization task. In this study, we propose a localness attention network, with simplicity and feasibility in mind, which circles different local regions in the source article as contributors in different decoding steps. To further strengthen the localness model, we share the semantic space of the encoder and decoder. The experimental results conducted on two benchmark datasets demonstrate the effectiveness and applicability of the proposed method in relation to several well-practiced works.

Typically, trajectories considered anomalous are the ones deviating from usual (e.g., traffic-dictated) driving patterns. However, this closed-set context fails to recognize the unknown anomalous trajectories, resulting in an insufficient self-motivated learning paradigm. In this study, we investigate the novel Anomalous Trajectory Recognition problem in an Open-world scenario (ATRO) and introduce a novel probabilistic Metric learning model, namely ATROM, to address it. Specifically, ATROM can detect the presence of unknown anomalous behavior in addition to identifying known behavior. It has a Mutual Interaction Distillation that uses contrastive metric learning to explore the interactive semantics regarding the diverse behavioral intents and a Probabilistic Trajectory Embedding that forces the trajectories with distinct behaviors to follow different Gaussian priors. More importantly, ATROM offers a probabilistic metric rule to discriminate between known and unknown behavioral patterns by taking advantage of the approximation of multiple priors. Experimental results on two large-scale trajectory datasets demonstrate the superiority of ATROM in addressing both known and unknown anomalous patterns.

As the third-generation neural networks, spiking neural networks (SNNs) have great potential on neuromorphic hardware because of their high energy efficiency. However, deep spiking reinforcement learning (DSRL), that is, the reinforcement learning (RL) based on SNNs, is still in its preliminary stage due to the binary output and the nondifferentiable property of the spiking function. To address these issues, we propose a deep spiking Q -network (DSQN) in this article. Specifically, we propose a directly trained DSRL architecture based on the leaky integrate-and-fire (LIF) neurons and deep Q -network (DQN). Then, we adapt a direct spiking learning algorithm for the DSQN. We further demonstrate the advantages of using LIF neurons in DSQN theoretically. Comprehensive experiments have been conducted on 17 top-performing Atari games to compare our method with the state-of-the-art conversion method. The experimental results demonstrate the superiority of our method in terms of performance, stability, generalization and energy efficiency. To the best of our knowledge, our work is the first one to achieve state-of-the-art performance on multiple Atari games with the directly trained SNN.

In the natural language processing family, learning representations is a pioneering study, especially in sequence-to-sequence tasks where outputs are generated, totally relying on the learning representations of source sequence. Generally, classic methods infer that each word occurring in the source sequence, having more or less influence on the target sequence, should all be considered when generating outputs. As the summarization task requires the output sequence to only retain the essence, classic full consideration of the source sequence may not work well on it, which calls for more suitable methods with the ability to discard the misleading noise words. Motivated by this, with both relevance retaining and redundancy removal in mind, we propose a summarization learning model by implementing an encoder with copious contextual information represented and a decoder with a selecting mechanism integrated. Specifically, we equip the encoder with an asynchronous bi directional parallel structure, in order to obtain abundant semantic representation. The decoder, different from the classic attention-based works, employs a self-aware context selecting mechanism to generate summary in a more productive way. We evaluate the proposed methods on three benchmark summarization corpora. The experimental results demonstrate the effectiveness and applicability of the proposed framework in relation to several well-practiced and state-of-the-art summarization methods.

Recent progress in text classification has been focused on high-resource languages such as English and Chinese.For low-resource languages, amongst them most African languages, the lack of well-annotated data and effective preprocessing, is hindering the progress and the transfer of successful methods.In this paper, we introduce two news datasets (KINNEWS and KIRNEWS) for multi-class classification of news articles in Kinyarwanda and Kirundi, two low-resource African languages.The two languages are mutually intelligible, but while Kinyarwanda has been studied in Natural Language Processing (NLP) to some extent, this work constitutes the first study on Kirundi.Along with the datasets, we provide statistics, guidelines for preprocessing, and monolingual and cross-lingual baseline models.Our experiments show that training embeddings on the relatively higher-resourced Kinyarwanda yields successful cross-lingual transfer to Kirundi.In addition, the design of the created datasets allows for a wider use in NLP beyond text classification in future studies, such as representation learning, cross-lingual learning with more distant languages, or as base for new annotations for tasks such as parsing, POS tagging, and NER.The datasets, stopwords, and pre-trained embeddings are publicly available at https://

Graph convolutional network (GCN), with its capability to update the current node features according to the features of its first-order adjacent nodes and edges, has achieved impressive performance in dependency capturing. But some important nodes from which we should figure out the dependencies are not first-order reachable, which calls for multi-layer GCNs for indirect relevance capturing. In this paper, we propose a novel weighted graph convolutional network by constructing a logical adjacency matrix which effectively solves the feature fusion of multi-hop relation without additional layers and parameters for relation extraction task. And we apply an Entity-Attention mechanism to enrich the entity pairs with more focused semantic information. Experimental results on TACRED and SemEval 2010 task 8 show that our model can take better advantage of the structural information in the dependency tree and produce better results than previous models.