paper-with-me

Papers

Multi-typed Objects Multi-view Multi-instance Multi-label Learning

2020-10-06 · Yuanlin Yang, Guoxian Yu, Jun Wang, Carlotta Domeniconi, Xiangliang Zhang

Multi-typed objects Multi-view Multi-instance Multi-label Learning (M4L) deals with interconnected multi-typed objects (or bags) that are made of diverse instances, represented with heterogeneous feature views and annotated with a set of non-exclusive but semantically related labels. M4L is more general and powerful than the typical Multi-view Multi-instance Multi-label Learning (M3L), which only accommodates single-typed bags and lacks the power to jointly model the naturally interconnected multi-typed objects in the physical world. To combat with this novel and challenging learning task, we develop a joint matrix factorization based solution (M4L-JMF). Particularly, M4L-JMF firstly encodes the diverse attributes and multiple inter(intra)-associations among multi-typed bags into respective data matrices, and then jointly factorizes these matrices into low-rank ones to explore the composite latent representation of each bag and its instances (if any). In addition, it incorporates a dispatch and aggregation term to distribute the labels of bags to individual instances and reversely aggregate the labels of instances to their affiliated bags in a coherent manner. Experimental results on benchmark datasets show that M4L-JMF achieves significantly better results than simple adaptions of existing M3L solutions on this novel problem.

📄 PDF Abstract BibTeX arXiv:2010.02539

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Label Learning

Similar Papers 제목 키워드 기반

Learning deep representation of multityped objects and tasks

2016-03-04 · Truyen Tran, Dinh Phung, Svetha Venkatesh

We introduce a deep multitask architecture to integrate multityped representations of multimodal objects. This multitype exposition is less abstract than the multimodal characterization, but more machine-friendly, and th…

Image RetrievalRetrieval

Neural Embedding Propagation on Heterogeneous Networks

2019-09-29 · Carl Yang, Jieyu Zhang, Jiawei Han

Classification is one of the most important problems in machine learning. To address label scarcity, semi-supervised learning (SSL) has been intensively studied over the past two decades, which mainly leverages data affi…

Network Embedding

Logical Semantics and Commonsense Knowledge: Where Did we Go Wrong, and How to Go Forward, Again

2018-08-06 · Walid S. Saba

We argue that logical semantics might have faltered due to its failure in distinguishing between two fundamentally very different types of concepts: ontological concepts, that should be types in a strongly-typed ontology…

Typed-RAG: Type-aware Multi-Aspect Decomposition for Non-Factoid Question Answering

2025-03-20 · Donggeon Lee, Ahjeong Park, Hyeri Lee, Hyeonseo Nam 외

Non-factoid question-answering (NFQA) poses a significant challenge due to its open-ended nature, diverse intents, and the need for multi-aspect reasoning, which renders conventional factoid QA approaches, including retr…

Question AnsweringRAGRetrievalRetrieval-augmented Generation

Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs

2026-09-01 · Wentao Zhang, Syed Shariyar Murtaza, Junaid Ahmad Bhatti, Utkarsh Soni 외 hf

Prompt optimization can improve multi-agent LLM systems, but the prompts being optimized often serve two entangled roles: generating task-relevant content and specifying execution-critical protocols, such as message rout…