GOOD: A Graph Out-of-Distribution Benchmark [NeurIPS 2022 Datasets and Benchmarks]

(ICLR 2022) Discovering Invariant Rationales for Graph Neural Networks

[NeurIPS 2022] Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs

Tools for exploiting Morphological Symmetries in robotics

[KDD'2023] "KGRec: Knowledge Graph Self-Supervised Rationalization for Recommendation"

[ICLR 2023, ICLR DG oral] PAIR, the optimizer and model selection criteria for OOD Generalization

Ratioanle-aware Graph Contrastive Learning codebase

[NeurIPS 2023] Understanding and Improving Feature Learning for Out-of-Distribution Generalization

This repo contains code for Invariant Grounding for Video Question Answering

[NeurIPS 2023] Does Invariant Graph Learning via Environment Augmentation Learn Invariance?

[ICLR'25 Spotlight] Revisiting Random Walks for Learning on Graphs (RWNN), in PyTorch

Causal Disentangled Recommendation Against Preference Shifts (TOIS), 2023

This repository provides implementations for sparse graph separation, power graph experiments, and chemical property prediction.

This repository contain code for research paper "Causal Discovery via Intrinsic invariant Conditional Probabilities"

Code for "Environment Diversification with Multi-head Neural Network for Invariant Learning" (NeurIPS 2022)

Regime-Invariant Specialist Pools (RISP): reward-independent specialist retention + episode-invariant decision-focused training for non-stationary markets. Theory, 11-arm experiments, three papers — honest nulls included. Companion to GAUSE.

Semantic Processing Unit (SPU): A neurosymbolic AI architecture replacing token prediction with differentiable matrix operators. It guarantees 100% logical accuracy, structural safety, and zero-error invariants on OOD data by decoupling semantic parsing from hardware-accelerated matrix algebra.

Basic Invariant Test Practice in Foundry

DELA - Disentanglement Learning Archive