PISA: Prioritized Invariant Subgraph Aggregation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ghasemi, Ali, Wani, Farooq Ahmad, Bucarelli, Maria Sofia, Silvestri, Fabrizio
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909930695426048
author Ghasemi, Ali
Wani, Farooq Ahmad
Bucarelli, Maria Sofia
Silvestri, Fabrizio
author_facet Ghasemi, Ali
Wani, Farooq Ahmad
Bucarelli, Maria Sofia
Silvestri, Fabrizio
contents Recent work has extended the invariance principle for out-of-distribution (OOD) generalization from Euclidean to graph data, where challenges arise due to complex structures and diverse distribution shifts in node attributes and topology. To handle these, Chen et al. proposed CIGA (Chen et al., 2022b), which uses causal modeling and an information-theoretic objective to extract a single invariant subgraph capturing causal features. However, this single-subgraph focus can miss multiple causal patterns. Liu et al. (2025) addressed this with SuGAr, which learns and aggregates diverse invariant subgraphs via a sampler and diversity regularizer, improving robustness but still relying on simple uniform or greedy aggregation. To overcome this, the proposed PISA framework introduces a dynamic MLP-based aggregation that prioritizes and combines subgraph representations more effectively. Experiments on 15 datasets, including DrugOOD (Ji et al., 2023), show that PISA achieves up to 5% higher classification accuracy than prior methods.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22435
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PISA: Prioritized Invariant Subgraph Aggregation
Ghasemi, Ali
Wani, Farooq Ahmad
Bucarelli, Maria Sofia
Silvestri, Fabrizio
Machine Learning
Recent work has extended the invariance principle for out-of-distribution (OOD) generalization from Euclidean to graph data, where challenges arise due to complex structures and diverse distribution shifts in node attributes and topology. To handle these, Chen et al. proposed CIGA (Chen et al., 2022b), which uses causal modeling and an information-theoretic objective to extract a single invariant subgraph capturing causal features. However, this single-subgraph focus can miss multiple causal patterns. Liu et al. (2025) addressed this with SuGAr, which learns and aggregates diverse invariant subgraphs via a sampler and diversity regularizer, improving robustness but still relying on simple uniform or greedy aggregation. To overcome this, the proposed PISA framework introduces a dynamic MLP-based aggregation that prioritizes and combines subgraph representations more effectively. Experiments on 15 datasets, including DrugOOD (Ji et al., 2023), show that PISA achieves up to 5% higher classification accuracy than prior methods.
title PISA: Prioritized Invariant Subgraph Aggregation
topic Machine Learning
url https://arxiv.org/abs/2511.22435