Copertina

Combating Spurious Correlations in Graph Interpretability via Self-Reflection

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cai, Kecheng, Xu, Chenyang, Peng, Chao, Huang, Jiafu, Liang, Qiyuan, Zheng, Irene
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction
di: Huang, Jiafu, et al.
Pubblicazione: (2026)

Mitigating Spurious Correlations via Disagreement Probability
di: Han, Hyeonggeun, et al.
Pubblicazione: (2024)

SCL-GNN: Towards Generalizable Graph Neural Networks via Spurious Correlation Learning
di: Zhang, Yuxiang, et al.
Pubblicazione: (2026)

The Pragmatic Frames of Spurious Correlations in Machine Learning: Interpreting How and Why They Matter
di: Bell, Samuel J., et al.
Pubblicazione: (2024)

Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotations
di: Le, Phuong Quynh, et al.
Pubblicazione: (2024)

Severing Spurious Correlations with Data Pruning
di: Mulchandani, Varun, et al.
Pubblicazione: (2025)

Revisiting Spurious Correlation in Domain Generalization
di: Qin, Bin, et al.
Pubblicazione: (2024)

Removing Spurious Correlation from Neural Network Interpretations
di: Fotouhi, Milad, et al.
Pubblicazione: (2024)

Self-Augmented Mixture-of-Experts for QoS Prediction
di: Cai, Kecheng, et al.
Pubblicazione: (2026)

Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation
di: Steinmann, David, et al.
Pubblicazione: (2024)

Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training
di: Moya, Christian, et al.
Pubblicazione: (2026)

Spurious Correlation-Aware Embedding Regularization for Worst-Group Robustness
di: Park, Subeen, et al.
Pubblicazione: (2025)

The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory
di: Tang, Luoxi, et al.
Pubblicazione: (2026)

A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima
di: Tang, Yiming, et al.
Pubblicazione: (2025)

Not Only the Last-Layer Features for Spurious Correlations: All Layer Deep Feature Reweighting
di: Hameed, Humza Wajid, et al.
Pubblicazione: (2024)

Open-Book Neural Algorithmic Reasoning
di: Li, Hefei, et al.
Pubblicazione: (2024)

Age Predictors Through the Lens of Generalization, Bias Mitigation, and Interpretability: Reflections on Causal Implications
di: Paul, Debdas, et al.
Pubblicazione: (2026)

Mitigating Spurious Correlations in NLI via LLM-Synthesized Counterfactuals and Dynamic Balanced Sampling
di: Jaimes, Christopher Román
Pubblicazione: (2025)

Correlating Time Series with Interpretable Convolutional Kernels
di: Chen, Xinyu, et al.
Pubblicazione: (2024)

Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
di: Wang, Chenyang, et al.
Pubblicazione: (2025)

Shortcut to Nowhere: Demystifying Deep Spurious Regression
di: Xu, Guanrong, et al.
Pubblicazione: (2026)

Faithful Interpretation for Graph Neural Networks
di: Hu, Lijie, et al.
Pubblicazione: (2024)

Identifying Spurious Correlations using Counterfactual Alignment
di: Cohen, Joseph Paul, et al.
Pubblicazione: (2023)

H-LDM: Hierarchical Latent Diffusion Models for Controllable and Interpretable PCG Synthesis from Clinical Metadata
di: Xu, Chenyang, et al.
Pubblicazione: (2025)

Exploring Correlations of Self-Supervised Tasks for Graphs
di: Fang, Taoran, et al.
Pubblicazione: (2024)

VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
di: Wang, Haozhe, et al.
Pubblicazione: (2025)

OPBench: A Graph Benchmark to Combat the Opioid Crisis
di: Ma, Tianyi, et al.
Pubblicazione: (2026)

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
di: Chen, Yiwei, et al.
Pubblicazione: (2025)

Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation
di: Liu, Chenruo, et al.
Pubblicazione: (2025)

Graph Similarity Computation via Interpretable Neural Node Alignment
di: Wang, Jingjing, et al.
Pubblicazione: (2024)

OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflection
di: Cui, Fan, et al.
Pubblicazione: (2024)

When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs
di: Wang, Shaowen, et al.
Pubblicazione: (2025)

Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs
di: El, Batu, et al.
Pubblicazione: (2025)

SIG: Efficient Self-Interpretable Graph Neural Network for Continuous-time Dynamic Graphs
di: Fang, Lanting, et al.
Pubblicazione: (2024)

TAGA: Text-Attributed Graph Self-Supervised Learning by Synergizing Graph and Text Mutual Transformations
di: Zhang, Zheng, et al.
Pubblicazione: (2024)

Rethinking Tokenized Graph Transformers for Node Classification
di: Chen, Jinsong, et al.
Pubblicazione: (2025)

AnyGraph: Graph Foundation Model in the Wild
di: Xia, Lianghao, et al.
Pubblicazione: (2024)

Bridging Explainability and Embeddings: BEE Aware of Spuriousness
di: Păduraru, Cristian Daniel, et al.
Pubblicazione: (2024)

Spurious Rewards: Rethinking Training Signals in RLVR
di: Shao, Rulin, et al.
Pubblicazione: (2025)

Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility
di: Barsbey, Melih, et al.
Pubblicazione: (2025)