# Dynamic Link Prediction for New Nodes in Temporal Graph Networks

arXiv: https://arxiv.org/abs/2310.09787 · HTML: https://mlsanity.com/paper/2310.09787/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 15 Oct 2023.

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

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [Learning Convolutional Neural Networks for Graphs](https://mlsanity.com/paper/1605.05273/) (2016)
- [Structured Sequence Modeling with Graph Convolutional Recurrent Networks](https://mlsanity.com/paper/1612.07659/) (2016)
- [Representation Learning for Dynamic Graphs: A Survey](https://mlsanity.com/paper/1905.11485/) (2019)
- [Meta-Learning: A Survey](https://mlsanity.com/paper/1810.03548/) (2018)
- [Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks](https://mlsanity.com/paper/2101.05974/) (2021)
- [Towards Better Dynamic Graph Learning: New Architecture and Unified Library](https://mlsanity.com/paper/2303.13047/) (2023)
- [Meta-GNN: On Few-shot Node Classification in Graph Meta-learning](https://mlsanity.com/paper/1905.09718/) (2019)
- [Graph Meta Learning via Local Subgraphs](https://mlsanity.com/paper/2006.07889/) (2020)
- [TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning](https://mlsanity.com/paper/2105.07944/) (2021)
- [Graph Few-shot Learning via Knowledge Transfer](https://mlsanity.com/paper/1910.03053/) (2019)
- [Temporal Network Embedding with Micro- and Macro-dynamics](https://mlsanity.com/paper/1909.04246/) (2019)
- [Meta-learning in natural and artificial intelligence](https://mlsanity.com/paper/2011.13464/) (2020)
- [Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures](https://mlsanity.com/paper/2002.12815/) (2020)
- [Meta-Graph: Few Shot Link Prediction via Meta Learning](https://mlsanity.com/paper/1912.09867/) (2019)
- [Encoder-Decoder Architecture for Supervised Dynamic Graph Learning: A Survey](https://mlsanity.com/paper/2203.10480/) (2022)

## Built on by (most cited first, 1 of 1)

- [Multi-Modal Parameter-Efficient Fine-tuning via Graph Neural Network](https://mlsanity.com/paper/2408.00290/) (2024)

## Abstract (arXiv)

Modelling temporal networks for dynamic link prediction of new nodes has many real-world applications, such as providing relevant item recommendations to new customers in recommender systems and suggesting appropriate posts to new users on social platforms. Unlike old nodes, new nodes have few historical links, which poses a challenge for the dynamic link prediction task. Most existing dynamic models treat all nodes equally and are not specialized for new nodes, resulting in suboptimal performances. In this paper, we consider dynamic link prediction of new nodes as a few-shot problem and propose a novel model based on the meta-learning principle to effectively mitigate this problem. Specifically, we develop a temporal encoder with a node-level span memory to obtain a new node embedding, and then we use a predictor to determine whether the new node generates a link. To overcome the few-shot challenge, we incorporate the encoder-predictor into the meta-learning paradigm, which can learn two types of implicit information during the formation of the temporal network through span adaptation and node adaptation. The acquired implicit information can serve as model initialisation and facilitate rapid adaptation to new nodes through a fine-tuning process on just a few links. Experiments on three publicly available datasets demonstrate the superior performance of our model compared to existing state-of-the-art methods.