View Space: Learning Representation across Arbitrary Graphs

2025-12-12 · Dooho Lee, Myeong Kong, Minho Jeong, Jaemin Yoo arxiv

Generalizing pretrained models to unseen datasets without retraining is a central challenge toward foundation models. Achieving fully inductive inference on numerical data is particularly difficult due to large variations in feature dimensionality and semantics across datasets. We observe that, in the presence of graph structure, numerical data admits a distinct structure-induced representational axis beyond the feature space, which we formalize as the view space. This view space enables a unified representation of graphs with heterogeneous features and motivates Graph View Transformation (GVT), a class of parametric mappings that can be shared across arbitrary graphs. We instantiate this framework with Recurrent GVT, an architecture for fully inductive node representation learning in node classification. Pretrained on OGBN-Arxiv and evaluated on 27 benchmarks, Recurrent GVT outperforms GraphAny, the prior fully inductive graph model, by +8.93%, and surpasses 12 individually tuned GNNs by at least +3.30%. These results establish the view space as a principled and practical foundation for learning across graphs with heterogeneous feature spaces. Code and checkpoints are available in https://github.com/dooho00/graph-view-space.

📄 PDF Abstract BibTeX arXiv:2512.11561

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning Node Classification

Bag-of-Vector Embeddings of Dependency Graphs for Semantic Induction

2017-09-30 · Diana Nicoleta Popa, James Henderson

Vector-space models, from word embeddings to neural network parsers, have many advantages for NLP. But how to generalise from fixed-length word vectors to a vector space for arbitrary linguistic structures is still uncle…

Natural Language Inference Semantic Textual Similarity Word Embeddings

Object-Centric Representation Learning with Generative Spatial-Temporal Factorization

2021-11-09 · NeurIPS 2021 12 · Li Nanbo, Muhammad Ahmed Raza, Hu Wenbin, Zhaole Sun 외

Learning object-centric scene representations is essential for attaining structural understanding and abstraction of complex scenes. Yet, as current approaches for unsupervised object-centric representation learning are …

Object Representation Learning

Learning Canonical View Representation for 3D Shape Recognition with Arbitrary Views

2021-08-16 · ICCV 2021 10 · Xin Wei, Yifei Gong, Fudong Wang, Xing Sun 외

In this paper, we focus on recognizing 3D shapes from arbitrary views, i.e., arbitrary numbers and positions of viewpoints. It is a challenging and realistic setting for view-based 3D shape recognition. We propose a cano…

3D Shape Recognition 3D Shape Representation

Learning Subspace-Preserving Sparse Attention Graphs from Heterogeneous Multiview Data

2026-05-12 · Jie Chen, Yuanbiao Gou, Chuanbin Liu, Zhu Wang 외 arxiv

The high-dimensional features extracted from large-scale unlabeled data via various pretrained models with diverse architectures are referred to as heterogeneous multiview data. Most existing unsupervised transfer learni…

Representation Learning Transfer Learning Graph Learning

A Self-supervised Mixed-curvature Graph Neural Network

2021-12-10 · Li Sun, Zhongbao Zhang, Junda Ye, Hao Peng 외

Graph representation learning received increasing attentions in recent years. Most of existing methods ignore the complexity of the graph structures and restrict graphs in a single constant-curvature representation space…

Contrastive Learning Graph Neural Network Graph Representation Learning Representation Learning