# Towards Open Temporal Graph Neural Networks

arXiv: https://arxiv.org/abs/2303.15015 · HTML: https://mlsanity.com/paper/2303.15015/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 27 Mar 2023.

## Builds on (most cited first, 26 of 26)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [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)
- [Rainbow Memory: Continual Learning with a Memory of Diverse Samples](https://mlsanity.com/paper/2103.17230/) (2021)
- [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020)
- [CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information](https://mlsanity.com/paper/2006.12013/) (2020)
- [Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks](https://mlsanity.com/paper/2101.05974/) (2021)
- [DynGEM: Deep Embedding Method for Dynamic Graphs](https://mlsanity.com/paper/1805.11273/) (2018)
- [Overcoming Catastrophic Forgetting in Graph Neural Networks](https://mlsanity.com/paper/2012.06002/) (2020)
- [GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily](https://mlsanity.com/paper/2110.15777/) (2021)
- [APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding](https://mlsanity.com/paper/2011.11545/) (2020)
- [Streaming Graph Neural Networks via Continual Learning](https://mlsanity.com/paper/2009.10951/) (2020)
- [TREND: TempoRal Event and Node Dynamics for Graph Representation Learning](https://mlsanity.com/paper/2203.14303/) (2022)
- [Sequential Scenario-Specific Meta Learner for Online Recommendation](https://mlsanity.com/paper/1906.00391/) (2019)
- [FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks](https://mlsanity.com/paper/2206.06561/) (2022)
- [Robust Knowledge Adaptation for Dynamic Graph Neural Networks](https://mlsanity.com/paper/2207.10839/) (2022)
- [On the Unreasonable Effectiveness of the Greedy Algorithm: Greedy Adapts to Sharpness](https://mlsanity.com/paper/2002.04063/) (2020)

## Built on by (most cited first, 13 of 13)

- [A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges](https://mlsanity.com/paper/2405.00476/) (2024)
- [Graph Domain Adaptation with Dual-branch Encoder and Two-level Alignment for Whole Slide Image-based Survival Prediction](https://mlsanity.com/paper/2411.14001/) (2024)
- [GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy](https://mlsanity.com/paper/2312.09708/) (2023)
- [PGODE: Towards High-quality System Dynamics Modeling](https://mlsanity.com/paper/2311.06554/) (2023)
- [Towards Continuous Reuse of Graph Models via Holistic Memory Diversification](https://mlsanity.com/paper/2406.07413/) (2024)
- [Graph Memory Learning: Imitating Lifelong Remembering and Forgetting of Brain Networks](https://mlsanity.com/paper/2407.19183/) (2024)
- [Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective](https://mlsanity.com/paper/2608.18104/) (2026)
- [Shared Growth of Graph Neural Networks via Prompted Free-direction Knowledge Distillation](https://mlsanity.com/paper/2307.00534/) (2023)
- [Filtration Surfaces for Dynamic Graph Classification](https://mlsanity.com/paper/2309.03616/) (2023)
- [A Selective Learning Method for Temporal Graph Continual Learning](https://mlsanity.com/paper/2503.01580/) (2025)
- [Deep Temporal Graph Clustering: A Comprehensive Benchmark and Datasets](https://mlsanity.com/paper/2601.12903/) (2026)
- [A General Benchmark Framework is Dynamic Graph Neural Network Need](https://mlsanity.com/paper/2401.06559/) (2024)
- [Invariant Graph Representations for Continuous-Time Dynamic Graphs Under Distribution Shifts](https://mlsanity.com/paper/2405.19062/) (2024)

## Abstract (arXiv)

Graph neural networks (GNNs) for temporal graphs have recently attracted increasing attentions, where a common assumption is that the class set for nodes is closed. However, in real-world scenarios, it often faces the open set problem with the dynamically increased class set as the time passes by. This will bring two big challenges to the existing dynamic GNN methods: (i) How to dynamically propagate appropriate information in an open temporal graph, where new class nodes are often linked to old class nodes. This case will lead to a sharp contradiction. This is because typical GNNs are prone to make the embeddings of connected nodes become similar, while we expect the embeddings of these two interactive nodes to be distinguishable since they belong to different classes. (ii) How to avoid catastrophic knowledge forgetting over old classes when learning new classes occurred in temporal graphs. In this paper, we propose a general and principled learning approach for open temporal graphs, called OTGNet, with the goal of addressing the above two challenges. We assume the knowledge of a node can be disentangled into class-relevant and class-agnostic one, and thus explore a new message passing mechanism by extending the information bottleneck principle to only propagate class-agnostic knowledge between nodes of different classes, avoiding aggregating conflictive information. Moreover, we devise a strategy to select both important and diverse triad sub-graph structures for effective class-incremental learning. Extensive experiments on three real-world datasets of different domains demonstrate the superiority of our method, compared to the baselines.