# When Molecular Similarity Works: Property Cliffs Reveal Hidden Errors

arXiv: https://arxiv.org/abs/2605.17265 · HTML: https://mlsanity.com/paper/2605.17265/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 17 May 2026.

## Builds on (most cited first, 25 of 25)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [SchNet: A continuous-filter convolutional neural network for modeling quantum interactions](https://mlsanity.com/paper/1706.08566/) (2017)
- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [Geometric and Physical Quantities Improve E(3) Equivariant Message Passing](https://mlsanity.com/paper/2110.02905/) (2021)
- [Large-Scale Chemical Language Representations Capture Molecular Structure and Properties](https://mlsanity.com/paper/2106.09553/) (2021)
- [GOOD: A Graph Out-of-Distribution Benchmark](https://mlsanity.com/paper/2206.08452/) (2022)
- [DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery](https://mlsanity.com/paper/2505.13940/) (2025)
- [Collaborative Expert LLMs Guided Multi-Objective Molecular Optimization](https://mlsanity.com/paper/2503.03503/) (2025)
- [Can Molecular Evolution Mechanism Enhance Molecular Representation?](https://mlsanity.com/paper/2501.15799/) (2025)
- [Graph-structured Small Molecule Drug Discovery Through Deep Learning: Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2502.08975/) (2025)
- [Equivariant Masked Position Prediction for Efficient Molecular Representation](https://mlsanity.com/paper/2502.08209/) (2025)
- [MolEvolve: LLM-Guided Evolutionary Search for Interpretable Molecular Optimization](https://mlsanity.com/paper/2603.24382/) (2026)
- [Topology-Aware Dynamic Reweighting for Distribution Shifts on Graph](https://mlsanity.com/paper/2406.01066/) (2024)
- [BSL: A Unified and Generalizable Multitask Learning Platform for Virtual Drug Discovery from Design to Synthesis](https://mlsanity.com/paper/2508.01195/) (2025)
- [PCEvo: Path-Consistent Molecular Representation via Virtual Evolutionary](https://mlsanity.com/paper/2601.19257/) (2026)

## Abstract (arXiv)

Accurate prediction of molecular properties underpins drug discovery and material design, yet even state-of-the-art models remain vulnerable to localized failure modes that aggregate metrics cannot detect. The places where molecular similarity should be most helpful are also places where standard evaluation can be most misleading. Property cliffs expose this gap: structurally similar molecules can still differ sharply in target property, so models with competitive overall performance may fail in high-risk local neighborhoods. To expose and mitigate this failure mode, CliffSplit, a cliff-aware evaluation protocol that constructs locally supported, cliff-exposed test cases, and CliffLoss, a model-agnostic train-only mitigation mechanism for cliff-sensitive errors, are introduced. Experiments on three QM9 targets and three MoleculeNet tasks across five backbones show that CliffSplit reveals at least 15% higher error in cliff-heavy QM9 regions, while CliffLoss reduces the cliff-to-smooth error gap by up to 30% on Lipophilicity and improves overall MAE by 9.7%. Together, these results turn molecular similarity failure from a descriptive anomaly into a benchmarked evaluation problem for molecular machine learning. The code is available at https://anonymous.4open.science/r/Cliff_Loss.