# H2CGL: Modeling Dynamics of Citation Network for Impact Prediction

arXiv: https://arxiv.org/abs/2305.01572 · HTML: https://mlsanity.com/paper/2305.01572/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 58 references that are in the map.
- First posted on arXiv 16 Apr 2023.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [ROLAND: Graph Learning Framework for Dynamic Graphs](https://mlsanity.com/paper/2208.07239/) (2022)
- [Dynamic Graph Convolutional Networks](https://mlsanity.com/paper/1704.06199/) (2017)
- [SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity](https://mlsanity.com/paper/1506.02594/) (2015)
- [DeepCas: an End-to-end Predictor of Information Cascades](https://mlsanity.com/paper/1611.05373/) (2016)
- [Quantifying Long-Term Scientific Impact](https://mlsanity.com/paper/1306.3293/) (2013)
- [A Survey of Information Cascade Analysis: Models, Predictions, and Recent Advances](https://mlsanity.com/paper/2005.11041/) (2020)
- [Predicting citation counts based on deep neural network learning techniques](https://mlsanity.com/paper/1809.04365/) (2018)
- [Instant Graph Neural Networks for Dynamic Graphs](https://mlsanity.com/paper/2206.01379/) (2022)
- [SChuBERT: Scholarly Document Chunks with BERT-encoding boost Citation Count Prediction](https://mlsanity.com/paper/2012.11740/) (2020)
- [CCGL: Contrastive Cascade Graph Learning](https://mlsanity.com/paper/2107.12576/) (2021)

## Built on by (most cited first, 4 of 4)

- [Forecasting high-impact research topics via machine learning on evolving knowledge graphs](https://mlsanity.com/paper/2402.08640/) (2024)
- [Predicting Scientific Impact Through Diffusion, Conformity, and Contribution Disentanglement](https://mlsanity.com/paper/2311.09262/) (2023)
- [GraphReview: Scientific Paper Evaluation via LLM-based Graph Evidence Expansion](https://mlsanity.com/paper/2605.27204/) (2026)
- [LLM4Impact: Integrating Heterogeneous Information for Scientific Impact Prediction](https://mlsanity.com/paper/2610.10138/) (2026)

## Abstract (arXiv)

The potential impact of a paper is often quantified by how many citations it will receive. However, most commonly used models may underestimate the influence of newly published papers over time, and fail to encapsulate this dynamics of citation network into the graph. In this study, we construct hierarchical and heterogeneous graphs for target papers with an annual perspective. The constructed graphs can record the annual dynamics of target papers' scientific context information. Then, a novel graph neural network, Hierarchical and Heterogeneous Contrastive Graph Learning Model (H2CGL), is proposed to incorporate heterogeneity and dynamics of the citation network. H2CGL separately aggregates the heterogeneous information for each year and prioritizes the highly-cited papers and relationships among references, citations, and the target paper. It then employs a weighted GIN to capture dynamics between heterogeneous subgraphs over years. Moreover, it leverages contrastive learning to make the graph representations more sensitive to potential citations. Particularly, co-cited or co-citing papers of the target paper with large citation gap are taken as hard negative samples, while randomly dropping low-cited papers could generate positive samples. Extensive experimental results on two scholarly datasets demonstrate that the proposed H2CGL significantly outperforms a series of baseline approaches for both previously and freshly published papers. Additional analyses highlight the significance of the proposed modules. Our codes and settings have been released on Github (https://github.com/ECNU-Text-Computing/H2CGL)