Cross-modal retrieval (CMR) has advanced considerably by mapping image and text features into a shared embedding space; however, these approaches still face two persistent challenges: (1) semantic sparsity, where discriminative cues are confined to localized regions, making it difficult to identify implicit visual evidence; and (2) ranking uncertainty under semantic ambiguity, where models struggle to maintain the correct retrieval order when candidates share similar contexts. To address these issues, we propose the Dual-Branch Multi-Granularity Network (DBMG) with Structured Contrastive Ranking, which enriches visual semantics by leveraging a multimodal large language model to generate auxiliary descriptions, aligns sparse cues through a dual-branch architecture capturing both global and local interactions, and enforces ranking consistency via a three-stage contrastive objective that progressively optimizes category clustering, instance alignment, and margin-based ranking. Extensive experiments on four standard CMR benchmarks demonstrate that DBMG outperforms 12 strong baselines, achieving an average 15.91% improvement in mAP, establishing a new state-of-the-art. The code is available at https://github.com/DMiC-Lab-HFUT/DBMG.

Graph convolutional networks (GCNs) are widely used in graph-based applications, such as social networks and recommendation systems. Nevertheless, large-scale graphs or deep aggregation layers in full-batch GCNs consume significant GPU memory, causing out-of-memory (OOM) errors on mainstream GPUs (e.g., 29-GB memory consumption on the Ogbn-products graph with five layers). The subgraph sampling methods reduce memory consumption to achieve lightweight GCNs by partitioning the graph into multiple subgraphs and sequentially training GCNs on each subgraph. However, these methods yield gaps among subgraphs, i.e., GCNs can only be trained based on subgraphs instead of global graph information, which reduces the accuracy of GCNs. In this article, we propose PromptGCN, a novel prompt-based lightweight GCN model to bridge the gaps among subgraphs. First, the learnable prompt embeddings are designed to obtain global information. Then, the prompts are attached to each subgraph to transfer the global information among subgraphs. Extensive experimental results on seven large-scale graphs demonstrate that PromptGCN exhibits superior performance compared to baselines. Notably, PromptGCN improves the accuracy of subgraph sampling methods by up to 5.48% on the Flickr dataset. Overall, PromptGCN is easily integrable with any subgraph sampling method to obtain a lightweight GCN model with higher accuracy.

Cognitive diagnosis (CD) aims to evaluate students’ cognitive states based on their interaction data, enabling downstream applications such as exercise recommendation and personalized learning guidance. However, existing methods often struggle with accuracy drops in cross-domain cognitive diagnosis (CDCD), a practical yet challenging task. While some efforts have explored exercise-aspect CDCD, such as cross-subject scenarios, they fail to address the broader dual-aspect nature of CDCD, encompassing both student- and exercise-aspect variations. This diversity creates significant challenges in developing a scenario-agnostic framework. To address these gaps, we propose PromptCD, a simple yet effective framework that leverages soft prompt transfer for cognitive diagnosis. PromptCD is designed to adapt seamlessly across diverse CDCD scenarios, introducing PromptCD-S for student-aspect CDCD and PromptCD-E for exercise-aspect CDCD. Extensive experiments on real-world datasets demonstrate the robustness and effectiveness of PromptCD, consistently achieving superior performance across various CDCD scenarios. Our work offers a unified and generalizable approach to CDCD, advancing both theoretical and practical understanding in this critical domain. The implementation of our framework is publicly available athttps://github.com/Publisher-PromptCD/PromptCD.

The superior performance of large-scale pre-trained models, such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformer (GPT), has received increasing attention in both academic and industrial research and has become one of the current research hotspots. A pre-trained model refers to a model trained on large-scale unlabeled data, whose purpose is to learn general language representation or features for fine-tuning or transfer learning in subsequent tasks. After pre-training is complete, a small amount of labeled data can be used to fine-tune the model for a specific task or domain. This two-stage method of “pre-training+fine-tuning” has achieved advanced results in natural language processing (NLP) tasks. Despite widespread adoption, existing fixed fine-tuning schemes that adapt well to one NLP task may perform inconsistently on other NLP tasks given that different tasks have different latent semantic structures. In this article, we explore the effectiveness of automatic fine-tuning pattern search for layer-wise learning rates from an evolutionary optimization perspective. Our goal is to use evolutionary algorithms to search for better task-dependent fine-tuning patterns for specific NLP tasks than typical fixed fine-tuning patterns. Experimental results on two real-world language benchmarks and three advanced pre-training language models show the effectiveness and generality of the proposed framework.

Point-of-Interest (POI) recommendation, pivotal for guiding users to their next interested locale, grapples with the persistent challenge of data sparsity. Whereas knowledge graphs (KGs) have emerged as a favored tool to mitigate the issue, existing KG-based methods tend to overlook two crucial elements: the intention steering users’ location choices and the high-order topological structure within the KG. In this paper, we craft an Intention-aware Knowledge Graph (IKG) that harmonizes users’ visit histories, movement trajectories, and location categories to model user intentions. Building upon IKG, our novel Intention-aware Knowledge Graph Network (IKGN) delves deeper into the POI recommendation by weighing and propagating node embeddings through an attention mechanism, capturing the unique locational intent of each user. A sequential model like GRU is then employed to ensure a comprehensive representation of users’ short- and long-term location preferences. An empirical study on two real-world datasets validates the effectiveness of our proposed IKGN, with it markedly outshining seven benchmark rival models in both Recall and NDCG metrics. The code of IKGN is available at https://github.com/Jungle123456/IKGN.

Large-scale pre-trained models such as GPT and BERT have demonstrated remarkable performance in information extraction tasks. However, their black-box nature poses challenges for reliability and interpretability. In contrast, rule- based extraction methods have better interpretability, but typically require domain experts to manually establish rules, limiting their generalization ability. In industry, there is often a demand for reliable knowledge extraction to reduce the time spent on manual verification of each piece of knowledge. In this paper, we explore the idea of combining GPT and symbolic-based methods to automatically discover reliable extraction patterns in text with a particular writing style. This method leverages the characteristics of high information density and similar writing patterns in text with a specific writing style to generate verifiable and reliable patterns. We conduct experiments on two datasets with a specific writing style to demonstrate its effectiveness, validating the idea of combining large models for reliable information extraction pattern discovery in the tested datasets.

Graph edge partitioning, which is essential for the efficiency of distributed graph computation systems, divides a graph into several balanced partitions within a given size to minimize the number of vertices to be cut. Existing graph partitioning models can be classified into two categories: offline and streaming graph partitioning models. The former requires global graph information during the partitioning, which is expensive in terms of time and memory for large-scale graphs. The latter creates partitions based solely on the received graph information. However, the streaming model may result in a lower partitioning quality compared with the offline model. Therefore, this study introduces a Local Graph Edge Partitioning model, which considers only the local information (i.e., a portion of a graph instead of the entire graph) during the partitioning. Considering only the local graph information is meaningful because acquiring complete information for large-scale graphs is expensive. Based on the Local Graph Edge Partitioning model, two local graph edge partitioning algorithms—Two-stage Local Partitioning and Adaptive Local Partitioning—are given. Experimental results obtained on 14 real-world graphs demonstrate that the proposed algorithms outperform rival algorithms in most tested cases. Furthermore, the proposed algorithms are proven to significantly improve the efficiency of the real graph computation system GraphX.

Graph edge partitioning divides the edges of an input graph into multiple balanced partitions of a given size to minimize the sum of vertices that are cut, which is critical to the performance of distributed graph computation platforms. Existing graph partitioning methods can be classified into two categories: offline graph partitioning and streaming graph partitioning. The first category requires global information for a graph during the partitioning, which is expensive in terms of time and memory for large-scale graphs. The second category, however, creates partitions solely based on the received edge information, which may result in lower performance than the offline methods. Therefore, in this study, the concept of local graph partitioning is introduced from local community detection to consider only local information, i.e., a part of the graph, instead of the graph as a whole, during the partitioning. The characteristic of storing only local information is important because real-world graphs are often large in scale, or they increase incrementally. Based on this idea, we propose a two-stage local partitioning algorithm, where the partitioning process is divided into two stages according to the structural changes of the current partition, and two different strategies are introduced to deal with the respective stages. Experimental results with real-world graphs demonstrate that the proposed algorithm outperforms the rival algorithms in most cases, including the state-of-the-art algorithm METIS.