arXiv Machine Learning October 22, 2026 By Tianjun Yao, Chen Xi, Xinyang Li, Lixian Zhong

Implicit Feature Reweighting for Label-Free Graph Generalization

Read the original on arXiv Machine Learning →

SCARCE is a label‑free representation‑learning framework that improves graph‑level out‑of‑distribution generalization. It uses an environment partition of training graphs—derived from metadata or self‑supervised clustering—to warm‑start a variational graph autoencoder and then applies an adversarial confusion mechanism that prevents a discriminator from distinguishing environments while preserving reconstruction fidelity. Theoretical analysis shows that this environment confusion contracts environment‑discriminative directions, effectively reweighting features to reduce reliance on spurious correlations, and experiments on synthetic and DrugOOD datasets demonstrate state‑of‑the‑art OOD performance among label‑free methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers

3d ago

Implicit Feature Reweighting for Label-Free Graph Generalization

Graph-level out-of-distribution (OOD) generalization is critical for deploying graph neural networks in real-world applications where distribution shifts are inevitable. Existing approaches typically...

rag benchmarks safety

arXiv Machine Learning

Oct 7

Complementary Supervised and Self-Supervised Representations for Out-of-Distribution Graph Learning

The paper investigates how self‑supervised graph representations can complement supervised ones for out‑of‑distribution (OOD) node classification. Two backbone‑agnostic frameworks are introduced: Co‑Train, which jointly learns and integrates supervised and SSL representations during training, and Dual‑Space Retrieval, which performs non‑parametric prediction in both representation spaces and fuses the results at inference. Experiments on four graph benchmarks with various GNN backbones and SSL objectives (DGI and GRACE) show that Co‑Train consistently outperforms strong supervised OOD baselines, while Dual‑Space Retrieval offers competitive, flexible performance, demonstrating that SSL provides complementary signals that improve OOD node classification.

By Qingying Hao, Zikang Chen, Chuxuan Hu, Jinyuan Jia, Bo Li, Gang Wang, Carl Gunter

benchmarks

Hugging Face Trending Papers

Oct 6

Complementary Supervised and Self-Supervised Representations for Out-of-Distribution Graph Learning

Out-of-distribution (OOD) generalization remains challenging for graph neural networks (GNNs), as graph distributions can vary substantially across time and domains. Supervised and self-supervised gra...

benchmarks

arXiv Machine Learning

Oct 5

Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation

arXiv:2610.02517v1 Announce Type: new Abstract: Graph-structured data plays a pivotal role in modeling complex relationships. However, real-world graphs are often incomplete due to data collection an...

By Yu Song, Zhigang Hua, Yan Xie, Bingheng Li, Jingzhe Liu, Bo Long, Jiliang Tang, Hui Liu

rag benchmarks

arXiv AI

Aug 6

NodeJEPA: Structure-Conditioned Latent Prediction for Node-Level Graph Self-Supervised Learning

arXiv:2608. 04381v1 Announce Type: cross Abstract: Self-supervised learning on graphs is largely shaped by contrastive methods that depend on carefully designed augmentations, and by generative methods that reconstruct node attributes in the input space.

By Tinghe Zhang, Jian Xu, Jiaheng Chen, Jiaxing Li, Yucheng Xiao, Qiang Wang

rag diffusion fine-tuning benchmarks

arXiv Machine Learning

Aug 11

CGRL: Causal-Guided Representation Learning for Node-Level Out-of-Distribution Generalization

arXiv:2603. 24304v2 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) deliver strong performance on graph tasks, but their accuracy drops significantly under out-of-distribution (OOD) scenarios.

By Bowen Lu, Liangqiang Yang, Teng Li, Kun Zhang

diffusion benchmarks

One email a morning, machine-written

Related stories

Implicit Feature Reweighting for Label-Free Graph Generalization

Complementary Supervised and Self-Supervised Representations for Out-of-Distribution Graph Learning

Complementary Supervised and Self-Supervised Representations for Out-of-Distribution Graph Learning

Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation

NodeJEPA: Structure-Conditioned Latent Prediction for Node-Level Graph Self-Supervised Learning

CGRL: Causal-Guided Representation Learning for Node-Level Out-of-Distribution Generalization