The corpus of knowledge that we have amassed is often fragmented in nature. That is, we only possess a mere fraction of understanding regarding various objects and lack a holistic view of the interconnections between them. Graph, a widely used model to represent data and relationships between data, encompasses significant amounts of fragmented knowledge. In this paper, we study fragmented graph pattern matching ($\mathsf {FPM}$for short) on large graphs, a typical problem of fragmented knowledge management. Given several query graphs,$\mathsf {FPM}$searches for matches whose subgraphs are isomorphic to the given query graphs and these subgraphs are connected in a specified way.$\mathsf {FPM}$plays a crucial role in detecting financial crime, identifying abnormal behavior and mining latent knowledge. We propose an algorithm$\mathsf {FraMatch}$, which adopts a traversal-based manner to adaptively identify matches for the given query graphs and enumerates the interconnections among these matches. To improve the efficiency of$\mathsf {FraMatch}$, an index, represented as a$k$-partite graph, is constructed to help organize the candidate matches. Additionally, several methods, including four filtering strategies, parallel optimization and a dynamic loading strategy, are proposed to further accelerate the algorithm and reduce memory usage. We conducted extensive experiments on 4 real graphs to validate$\mathsf {FraMatch}$. The results demonstrate that$\mathsf {FraMatch}$outperforms its comparisons 2000× in running time and reduces memory usage by 8% on average. A real application on anti-money laundering further verifies the effectiveness of$\mathsf {FPM}$. To the best of our knowledge, this is the first study on$\mathsf {FPM}$on large graphs.

Sequential recommendation is essential in modern recommender systems, focusing on effectively extracting and expressing user representations. Most existing methods rely on deep neural networks that employ a single vector for user interests, neglecting their multi-dimensional nature. This limitation hampers the accurate representation of user preferences. Meanwhile, with the development of deep learning and large models, the growing complexity of deep learning models increases hardware and training costs. In this paper, SCAD (Advancing Sequence Augmentation with Coupling Attention Dynamic Routing), a neighbor-based sequential recommender model, is proposed to tackle these challenges, and it can be regarded as a lightweight recommender system model. SCAD features three main components: the Neighbor Interest Activation (NIA) module, which enhances user representation by exploring similar users; the Coupling Attention Dynamic Routing (CAD) module, which uses a Capsule Network to determine the optimal representation strategy; and the “Interest Merge” module, which integrates single- and multi-interest information for improved preference extraction. Generally speaking, SCAD is superior to most existing methods in constructing user interests, and significantly improves the accuracy of recommendation. Extensive experiments on two real-world benchmarks demonstrate that SCAD outperforms existing top-performance methods in terms of recommendation accuracy.