English
Related papers

Related papers: IBMEA: Exploring Variational Information Bottlenec…

200 papers

Multimodal entity linking (MEL) aims to utilize multimodal information (usually textual and visual information) to link ambiguous mentions to unambiguous entities in knowledge base. Current methods facing main issues: (1)treating the entire…

Artificial Intelligence · Computer Science 2024-04-11 Shezheng Song , Shasha Li , Shan Zhao , Xiaopeng Li , Chengyu Wang , Jie Yu , Jun Ma , Tianwei Yan , Bin Ji , Xiaoguang Mao

Developing effective path representations has become increasingly essential across various fields within intelligent transportation. Although pre-trained path representation learning models have shown improved performance, they…

Machine Learning · Computer Science 2025-01-03 Ronghui Xu , Hanyin Cheng , Chenjuan Guo , Hongfan Gao , Jilin Hu , Sean Bin Yang , Bin Yang

Temporal Entity Alignment (TEA), which aims to identify equivalent entities across Temporal Knowledge Graphs (TKGs), is crucial for integrating knowledge facts from multiple sources. However, existing TEA models often fail to capture the…

Information Retrieval · Computer Science 2026-05-19 Jiayun Li , Wen Hua , Shiqi Fan , Fengmei Jin , Haiyang Jiang , Xue Li

Fusing data from multiple modalities provides more information to train machine learning systems. However, it is prohibitively expensive and time-consuming to label each modality with a large amount of data, which leads to a crucial problem…

Computer Vision and Pattern Recognition · Computer Science 2020-07-15 Xinwei Sun , Yilun Xu , Peng Cao , Yuqing Kong , Lingjing Hu , Shanghang Zhang , Yizhou Wang

The key challenge in unaligned multimodal language sequences lies in effectively integrating information from various modalities to obtain a refined multimodal joint representation. Recently, the disentangle and fuse methods have achieved…

Computation and Language · Computer Science 2024-09-20 Fan Qian , Jiqing Han , Jianchen Li , Yongjun He , Tieran Zheng , Guibin Zheng

Entity alignment (EA) aims to find entities in different knowledge graphs (KGs) that refer to the same object in the real world. Recent studies incorporate temporal information to augment the representations of KGs. The existing methods for…

Artificial Intelligence · Computer Science 2022-09-21 Li Cai , Xin Mao , Meirong Ma , Hao Yuan , Jianchao Zhu , Man Lan

Semi-supervised entity alignment (EA) is a practical and challenging task because of the lack of adequate labeled mappings as training data. Most works address this problem by generating pseudo mappings for unlabeled entities. However, they…

Machine Learning · Computer Science 2023-11-09 Feng Xie , Xin Song , Xiang Zeng , Xuechen Zhao , Lei Tian , Bin Zhou , Yusong Tan

Broadcast and media organizations increasingly rely on artificial intelligence to automate the labor-intensive processes of content indexing, tagging, and metadata generation. However, existing AI systems typically operate on a single…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Yassir Benhammou , Suman Kalyan , Sujay Kumar

We present M$^3$-VQA, a novel knowledge-based Visual Question Answering (VQA) benchmark, to enhance the evaluation of multimodal large language models (MLLMs) in fine-grained multimodal entity understanding and complex multi-hop reasoning.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Jiatong Ma , Longteng Guo , Yuchen Liu , Zijia Zhao , Dongze Hao , Xuanxu Lin , Jing Liu

We present MMKG, a collection of three knowledge graphs that contain both numerical features and (links to) images for all entities as well as entity alignments between pairs of KGs. Therefore, multi-relational link prediction and entity…

Artificial Intelligence · Computer Science 2019-03-14 Ye Liu , Hui Li , Alberto Garcia-Duran , Mathias Niepert , Daniel Onoro-Rubio , David S. Rosenblum

Generative models for multimodal data permit the identification of latent factors that may be associated with important determinants of observed data heterogeneity. Common or shared factors could be important for explaining variation across…

Machine Learning · Statistics 2024-03-12 Kaspar Märtens , Christopher Yau

Variational Autoencoder is a scalable method for learning latent variable models of complex data. It employs a clear objective that can be easily optimized. However, it does not explicitly measure the quality of learned representations. We…

Machine Learning · Computer Science 2020-05-29 Andriy Serdega , Dae-Shik Kim

In recent several years, the information bottleneck (IB) principle provides an information-theoretic framework for deep multi-view clustering (MVC) by compressing multi-view observations while preserving the relevant information of multiple…

Information Theory · Computer Science 2024-03-26 Xiaoqiang Yan , Zhixiang Jin , Fengshou Han , Yangdong Ye

Semantic embedding has been widely investigated for aligning knowledge graph (KG) entities. Current methods have explored and utilized the graph structure, the entity names and attributes, but ignore the ontology (or ontological schema)…

Computation and Language · Computer Science 2021-05-25 Yuejia Xiang , Ziheng Zhang , Jiaoyan Chen , Xi Chen , Zhenxi Lin , Yefeng Zheng

Many recent datasets contain a variety of different data modalities, for instance, image, question, and answer data in visual question answering (VQA). When training deep net classifiers on those multi-modal datasets, the modalities get…

Computer Vision and Pattern Recognition · Computer Science 2020-10-22 Itai Gat , Idan Schwartz , Alexander Schwing , Tamir Hazan

Reinforcement learning has achieved promising results on robotic control tasks but struggles to leverage information effectively from multiple sensory modalities that differ in many characteristics. Recent works construct auxiliary losses…

Machine Learning · Computer Science 2024-10-24 Bang You , Huaping Liu

Medical foundation models (MFMs) aim to learn universal representations from multimodal medical images that can generalize effectively to diverse downstream clinical tasks. However, most existing MFMs suffer from information ambiguity that…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yihang Liu , Longzhen Yang , Jiaxiong Yang , Ying Wen , Lianghua He , Heng Tao Shen

Multimodal knowledge editing (MKE) aims to correct the internal knowledge of large vision-language models after deployment, yet the behavioral patterns of post-edit models remain underexplored. In this paper, we identify a systemic failure…

Computation and Language · Computer Science 2026-05-08 Shu Wu , Xiaotian Ye , Xinyu Mou , Dongsheng Liu , Xiaohan Wang , Mengqi Zhang

The presence of symmetries imposes a stringent set of constraints on a system. This constrained structure allows intelligent agents interacting with such a system to drastically improve the efficiency of learning and generalization, through…

Information Theory · Computer Science 2024-10-03 Hippolyte Charvin , Nicola Catenacci Volpi , Daniel Polani

Event argument extraction (EAE) aims to extract arguments with given roles from texts, which have been widely studied in natural language processing. Most previous works have achieved good performance in specific EAE datasets with dedicated…

Computation and Language · Computer Science 2022-09-07 Jie Zhou , Qi Zhang , Qin Chen , Liang He , Xuanjing Huang