Multimodal Sentiment Analysis (MSA) and Emotion Recognition in Conversations (ERC) have rapidly developed into pivotal tasks in artificial intelligence. Large Language Models (LLMs) offer powerful semantic reasoning and computational capabilities, showing great potential for understanding emotional content. However, when applied to multimodal sentiment data, LLMs face significant challenges, including the inability to directly process heterogeneous data, difficulties in coping with feature misalignment and suboptimal cross-modal fusion. To address these challenges, we propose a novel multimodal sentiment inference framework named ATGFB-MFF which grounded in fiber bundle theory. This method decomposes multimodal features into an adaptive text-guided shared semantic space and fiber offset spaces to achieve structured alignment and fusion. Then the fused features are converted into structured pseudo-token sequences for effective inference via frozen LLMs. We also introduce two loss functions respectively called shared space consistency loss and fiber offset regularization loss which are used to improve representation stability. Extensive experiments on four benchmark datasets demonstrate that ATGFB-MFF consistently outperforms state-of-the-art baselines. These results highlight the efficacy of geometric structural modeling in unlocking the potential of LLMs for multimodal sentiment inference.

Network embedding, which aims at learning low-dimensional representations of nodes in a network, has drawn much attention for various network mining tasks, ranging from link prediction to node classification. In addition to network topological information, there also exist rich attributes associated with network structure, which exerts large effects on the network formation. Hence, many efforts have been devoted to tackling attributed network embedding tasks. However, they are also limited in their assumption of static network data as they do not account for evolving network structure as well as changes in the associated attributes. Furthermore, scalability is a key factor when performing representation learning on large-scale networks with huge number of nodes and edges. In this work, we address these challenges by developing the DRLAN-Dynamic Representation Learning framework for large-scale Attributed Networks. The DRLAN model generalizes the dynamic attributed network embedding from two perspectives: First, we develop an integrative learning framework with an offline batch embedding module to preserve both the node and attribute proximities, and online network embedding model that recursively updates learned representation vectors. Second, we design a recursive pre-projection mechanism to efficiently model the attribute correlations based on the associative property of matrices. Finally, we perform extensive experiments on three real-world network datasets to show the superiority of DRLAN against state-of-the-art network embedding techniques in terms of both effectiveness and efficiency. The source code is available at: https://github.com/ZhijunLiu95/DRLAN.

The increasing pervasiveness of object tracking technologies leads to huge volumes of spatio-temporal data collected in the form of trajectory streams. The discovery of useful group patterns from moving objects' movement behaviors in trajectory streams is critical for real time applications ranging from transportation management to military surveillance. In this work we propose a novel type of group pattern, called evolving group, which models the unusual group events of moving objects that travel together within density connected clusters in evolving streaming trajectories. Our theoretical analysis and empirical study on the Beijing Taxi data demonstrate its effectiveness in capturing development, evolution and trend of group events of moving objects in streaming context. Furthermore, we propose a discovery framework that efficiently supports online detection of evolving groups over massive-scale trajectory streams using sliding window. It contains three phases along with a set of novel optimization techniques designed to minimize the computation costs. Our comprehensive empirical study demonstrates that our discovery framework is effective and efficient on real-world high volume trajectory streams.