Distilling and Adapting: A Topology-Aware Framework for Zero-Shot Interaction Prediction in Multiplex Biological Networks

TL;DR

This work proposes a novel framework for zero-shot interaction prediction in MBNs by leveraging context-aware representation learning and knowledge distillation, which outperforms state-of-the-art methods in interaction prediction for MBNs.

Abstract

Multiplex Biological Networks (MBNs), which represent multiple interaction types between entities, are crucial for understanding complex biological systems. Yet, existing methods often inadequately model multiplexity, struggle to integrate structural and sequence information, and face difficulties in zero-shot prediction for unseen entities with no prior neighbourhood information. To address these limitations, we propose a novel framework for zero-shot interaction prediction in MBNs by leveraging context-aware representation learning and knowledge distillation. Our approach leverages domain-specific foundation models to generate enriched embeddings, introduces a topology-aware graph tokenizer to capture multiplexity and higher-order connectivity, and employs contrastive learning to align embeddings across modalities. A teacher-student distillation strategy further enables robust zero-shot generalization. Experimental results demonstrate that our framework outperforms state-of-the-art methods in interaction prediction for MBNs, providing a powerful tool for exploring various biological interactions and advancing personalized therapeutics.

Figures (7)

• Figure 1: Illustration of an example multiplex network and its supra-adjacency matrix. $A_1$ and $A_2$ are the layer-specific adjacency matrices for layer $1$ and $2$, $C$ is the inter-layer adjacency matrix, and $\hat{A}$ is the supra-adjacency matrix that represents the example multiplex network $\mathcal{G}$.
• Figure 2: (a) The overall training workflow of CAZI-MBN. (b) Two inference settings in CAZI-MBN: Transductive and zero-shot.
• Figure 3: Illustration of the CAE module.
• Figure 4: Average metric-wise performance drop across all five datasets when each module is ablated.
• Figure 5: Interaction type-specific performance analysis across five datasets, evaluated by prediction accuracy.