Active Sampling for Node Attribute Completion on Graphs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916566822551552 |
|---|---|
| author | Liu, Benyuan Chen, Xu Wang, Yanfeng Zhang, Ya Cao, Zhi Tsang, Ivor |
| author_facet | Liu, Benyuan Chen, Xu Wang, Yanfeng Zhang, Ya Cao, Zhi Tsang, Ivor |
| contents | Node attribute, a type of crucial information for graph analysis, may be partially or completely missing for certain nodes in real world applications. Restoring the missing attributes is expected to benefit downstream graph learning. Few attempts have been made on node attribute completion, but a novel framework called Structure-attribute Transformer (SAT) was recently proposed by using a decoupled scheme to leverage structures and attributes. SAT ignores the differences in contributing to the learning schedule and finding a practical way to model the different importance of nodes with observed attributes is challenging. This paper proposes a novel AcTive Sampling algorithm (ATS) to restore missing node attributes. The representativeness and uncertainty of each node's information are first measured based on graph structure, representation similarity and learning bias. To select nodes as train samples in the next optimization step, a weighting scheme controlled by Beta distribution is then introduced to linearly combine the two properties. Extensive experiments on four public benchmark datasets and two downstream tasks have shown the superiority of ATS in node attribute completion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_08450 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Active Sampling for Node Attribute Completion on Graphs Liu, Benyuan Chen, Xu Wang, Yanfeng Zhang, Ya Cao, Zhi Tsang, Ivor Artificial Intelligence Social and Information Networks Node attribute, a type of crucial information for graph analysis, may be partially or completely missing for certain nodes in real world applications. Restoring the missing attributes is expected to benefit downstream graph learning. Few attempts have been made on node attribute completion, but a novel framework called Structure-attribute Transformer (SAT) was recently proposed by using a decoupled scheme to leverage structures and attributes. SAT ignores the differences in contributing to the learning schedule and finding a practical way to model the different importance of nodes with observed attributes is challenging. This paper proposes a novel AcTive Sampling algorithm (ATS) to restore missing node attributes. The representativeness and uncertainty of each node's information are first measured based on graph structure, representation similarity and learning bias. To select nodes as train samples in the next optimization step, a weighting scheme controlled by Beta distribution is then introduced to linearly combine the two properties. Extensive experiments on four public benchmark datasets and two downstream tasks have shown the superiority of ATS in node attribute completion. |
| title | Active Sampling for Node Attribute Completion on Graphs |
| topic | Artificial Intelligence Social and Information Networks |
| url | https://arxiv.org/abs/2501.08450 |