mlsanityData to 7 Oct 2026

PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Prediction

arXiv 2310.00614 ↗First posted 1 Oct 2023cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Molecular property prediction (MPP) plays a crucial role in biomedical applications, but it often encounters challenges due to a scarcity of labeled data. Existing works commonly adopt gradient-based strategy to update a large amount of parameters for task-level adaptation. However, the increase of adaptive parameters can lead to overfitting and poor performance. Observing that graph neural network (GNN) performs well as both encoder and predictor, we propose PACIA, a parameter-efficient GNN adapter for few-shot MPP. We design a unified adapter to generate a few adaptive parameters to modulate the message passing process of GNN. We then adopt a hierarchical adaptation mechanism to adapt the encoder at task-level and the predictor at query-level by the unified GNN adapter. Extensive results show that PACIA obtains the state-of-the-art performance in few-shot MPP problems, and our proposed hierarchical adaptation mechanism is rational and effective.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 30 of its 45 references that are in the map. First posted on arXiv 1 Oct 2023.

Builds on

30 of 45 references.

References · 30

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2018How Powerful are Graph Neural Networks?cited by 4,355
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  5. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  8. 2016HyperNetworkscited by 1,003
  9. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  10. 2019Meta-Learning with Implicit Gradientscited by 523
  11. 2020Principal Neighbourhood Aggregation for Graph Netscited by 477
  12. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
18 more
  1. 2019Analyzing Learned Molecular Representations for Property Predictioncited by 373
  2. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  3. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  4. 2019Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processescited by 131
  5. 2021Self-supervised Graph-level Representation Learning with Local and Global Structurecited by 125
  6. 2019Edge-labeling Graph Neural Network for Few-shot Learningcited by 114
  7. 2019Meta-Learning without Memorizationcited by 92
  8. 2020Molecule Attention Transformercited by 92
  9. 2016Low Data Drug Discovery with One-shot Learningcited by 91
  10. 2021Few-Shot Graph Learning for Molecular Property Predictioncited by 81
  11. 2019GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulationcited by 75
  12. 2021Property-Aware Relation Networks for Few-Shot Molecular Property Predictioncited by 41
  13. 2021Task-adaptive Neural Process for User Cold-Start Recommendationcited by 32
  14. 2023Context-enriched molecule representations improve few-shot drug discoverycited by 23
  15. 2022Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Predictioncited by 21
  16. 2022HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworkscited by 16
  17. 2023Graph Sampling-based Meta-Learning for Molecular Property Predictioncited by 10
  18. 2020Molecule Property Prediction and Classification with Graph Hypernetworkscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2025Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a surveycited by 4
  2. 2024Learning to Learn with Contrastive Meta-Objectivecited by 3
  3. 2026SwiftRepertoire: Few-Shot Immune-Signature Synthesis via Dynamic Kernel Codescited by 0
  4. 2026CalibHyper: Chance-Corrected Relational Hypergraphs for Few-Shot Molecular Property Predictioncited by 0