Sequential recommendation is pivotal to personalized services by modeling the temporal dynamics of user behavior. However, existing methods often rely on abundant interactions, making it unreliable under sparse user interactions. Recent attempts to integrate sequential signals with orderless structural cues (e.g., global co-occurrence) help alleviate this issue but typically adopt tight fusion, which can dilute order-aware signals. To address this, we propose LOOM (Loosely-Coupled Ordered-Orderless Modeling), a structure-agnostic guidance module for sequential recommenders. LOOM is sequence-first: The sequential backbone acts as a teacher, guiding orderless carriers via one-way KL divergence, with recency-aware weighting and confidence-modulated strength to filter stale or uncertain relations. This preserves temporal modeling while selectively incorporating complementary orderless knowledge. Experiments on four public datasets and various sequential architectures show that LOOM outperforms state-of-the-art methods. Code is available at https://github.com/cqu-jia/LOOM.

Sequential recommenders are integral to many applications yet remain vulnerable to model extraction attacks, in which adversaries can recover information about the deployed model by issuing queries to a black-box without internal access. From the attacker's perspective, existing studies impose a fixed and limited query budget but overlook optimal allocation, resulting in redundant or low-value requests. Furthermore, the scarce data obtained through these costly queries is typically handled by crude random sampling, resulting in low diversity and information coverage with actual data. In this paper, we propose a novel approach, named Budget and Frequency Controlled Cost-Aware Model Extraction Attack (BECOME), for extracting black-box sequential recommenders, which extends the standard extraction framework with two cost-aware innovations: Feedback-Driven Dynamic Budgeting periodically evaluates the victim model to refine query allocation and steer sequence generation adaptively. Rank-Aware Frequency Controlling integrates frequency constraints with ranking guidance in the next-item sampler to select high-value items and broaden information coverage. Experiments on public datasets and representative sequential recommender architectures demonstrate that our method achieves superior extraction performance. Our code is released at https://github.com/Loche2/BECOME.

Large Language Models (LLMs) have recently shown promise in Time Series Forecasting (TSF) by effectively capturing intricate time-domain dependencies. However, our preliminary experiments reveal that standard LLM-based approaches often fail to capture global correlations, limiting predictive performance. We found that embedding frequency-domain signals smooths weight distributions and enhances structured correlations by clearly separating global trends (low-frequency components) from local variations (high-frequency components). Building on these insights, we propose FreqLLM, a novel framework that integrates frequency-domain semantic alignment into LLMs to refine prompts for improved time series analysis. By bridging the gap between frequency signals and textual embeddings, FreqLLM effectively captures multi-scale temporal patterns and provides more robust forecasting results. Extensive experiments on benchmark datasets demonstrate that FreqLLM outperforms state-of-the-art TSF methods in both accuracy and generalization. The code is available at https://github.com/biya0105/FreqLLM.

Large-scale graph data has demonstrated significant success in graph representation learning, but the associated high computational cost and inefficiency hinder its widespread adoption across diverse applications. Graph condensation has emerged as a promising solution to reduce time and memory demands while preserving generalization performance comparable to the original graph. Although existing graph condensation methods have proven effective, they are constrained by their reliance on repeatedly optimizing a condensed graph at a fixed scale, which demands significant computational resources and lacks flexibility to accommodate varying training requirements. This motivates us to explore alternative approaches that incrementally refine and expand condensed graphs.

Deep hashing technology has recently become an essential tool for cross-modal retrieval on large-scale datasets. However, their performances heavily depend on accurate annotations to train the hashing model. In real applications, we usually only obtain low-quality label annotations owing to labor and time consumption limitations. To mitigate the performance degradation caused by noisy labels, in this paper, we propose a robust deep hashing method, called deep hashing with ranking learning (DHRL), for cross-modal retrieval. The proposed DHRL method consists of a refined semantic concept alignment module and a ranking-swapping module. In this first module, we adopt two transformers to perform the semantic alignment tasks between different modalities on a set of refined concepts, and then convert them into hash codes to reduce heterogeneous differences between multimodalities. The second module first identifies the noisy labels in the training set and ranks them according to ranking loss. Then it swaps the ranking information of different modal network branches. Unlike existing robust hashing methods for assuming noise distribution, our proposed DHRL method requires no prior assumptions for the input data. Extensive experiments on three benchmark datasets have shown that our proposed DHRL method has stronger advantages over other state-of-the-art hashing methods.

Cross-modal hashing retrieval approaches have received extensive attention owing to their storage superiority and retrieval efficiency. To achieve better retrieval performances, hashing methods seek to embed more semantic information of multi-modal data into hash codes. Existing deep cross-modal hashing methods typically learn hash functions from the similarity of paired data to generate hash codes. However, such locally-oriented learning methods often suffer from low efficiency and incomplete acquisition of semantic information. To address these challenges, this paper presents a novel deep hashing approach, called Proxy-based Graph Convolutional Hashing (PGCH), for cross-modal retrieval. Specifically, we use global similarity to construct proxy hash codes for two different modalities. This strategy of these proxy hash codes ensures that they include data points with significant distribution differences. It helps to match data from different modalities to different proxy hash codes, which can capture the global similarity of multi-modal hash codes and improve the efficiency of hash code learning. Subsequently, we employ a multi-modal contrastive loss to learn the global similarity. Furthermore, by constructing a proxy hash matrix from the proxy hash codes, we apply graph convolution to efficiently narrow the gap between different modalities, leading to a substantial improvement in retrieval performance for cross-modal retrieval tasks. The comprehensive experiments on four benchmark multimedia datasets demonstrate that our PGCH approach achieves better retrieval performances than a bundle of state-of-the-art hashing approaches.