T- Hop: A framework for studying the importance path information in molecular graphs for chemical property prediction
Not on the map. Why?
Abstract (arXiv)
This paper studies the usefulness of incorporating path information in predicting chemical properties from molecular graphs, in the domain of QSAR (Quantitative Structure-Activity Relationship). Towards this, we developed a GNN-style model which can be toggled to operate in one of two modes: a non-degenerate mode which incorporates path information, and a degenerate mode which leaves out path information. Thus, by comparing the performance of the non-degenerate mode versus the degenerate mode on relevant QSAR datasets, we were able to directly assess the significance of path information on those datasets. Our results corroborate previous works, by suggesting that the usefulness of path information is datasetdependent. Unlike previous studies however, we took the very first steps towards building a model that could predict upfront whether or not path information would be useful for a given dataset at hand. Moreover, we also found that, albeit its simplicity, the degenerate mode of our model yielded rather surprising results, which outperformed more sophisticated SOTA models in certain cases.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 59 references that are in the map. First posted on arXiv 29 Jun 2024.
Builds on
29 of 59 references.
References · 29
- 2017Graph Attention Networkscited by 8,854
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
- 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
- 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
- 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
- 2021How Attentive are Graph Attention Networks?cited by 818
- 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
- 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
- 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 443
- 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
- 2018Tune: A Research Platform for Distributed Model Selection and Trainingcited by 395
17 more
- 2019Analyzing Learned Molecular Representations for Property Predictioncited by 373
- 2020ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Predictioncited by 332
- 2021Do Transformers Really Perform Bad for Graph Representation?cited by 318
- 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
- 2016Molecular Graph Convolutions: Moving Beyond Fingerprintscited by 238
- 2015Order Matters: Sequence to sequence for setscited by 236
- 2021Large-Scale Chemical Language Representations Capture Molecular Structure and Propertiescited by 203
- 2023Do We Really Need Complicated Model Architectures For Temporal Networks?cited by 141
- 2019Label Efficient Semi-Supervised Learning via Graph Filteringcited by 46
- 2023Gotta be SAFE: A New Framework for Molecular Designcited by 45
- 2015Compositional Vector Space Models for Knowledge Base Completioncited by 33
- 2023Path Neural Networks: Expressive and Accurate Graph Neural Networkscited by 32
- 2021Learning Attributed Graph Representations with Communicative Message Passing Transformercited by 20
- 2022Geodesic Graph Neural Network for Efficient Graph Representation Learningcited by 19
- 2019Power up! Robust Graph Convolutional Network via Graph Poweringcited by 15
- 2020RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Designcited by 6
- 2021ChemiRise: a data-driven retrosynthesis enginecited by 1
Built on by
Not cited yet.