# Unlocking Multi-Modal Potentials for Link Prediction on Dynamic Text-Attributed Graphs

arXiv: https://arxiv.org/abs/2502.19651 · HTML: https://mlsanity.com/paper/2502.19651/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## 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)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [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)
- [Representation Learning for Dynamic Graphs: A Survey](https://mlsanity.com/paper/1905.11485/) (2019)
- [Towards Better Dynamic Graph Learning: New Architecture and Unified Library](https://mlsanity.com/paper/2303.13047/) (2023)
- [Do We Really Need Complicated Model Architectures For Temporal Networks?](https://mlsanity.com/paper/2302.11636/) (2023)
- [Temporal Graph Benchmark for Machine Learning on Temporal Graphs](https://mlsanity.com/paper/2307.01026/) (2023)
- [Session-based Social Recommendation via Dynamic Graph Attention Networks](https://mlsanity.com/paper/1902.09362/) (2019)
- [Long Range Propagation on Continuous-Time Dynamic Graphs](https://mlsanity.com/paper/2406.02740/) (2024)
- [DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphs](https://mlsanity.com/paper/2406.12072/) (2024)
- [On the Feasibility of Simple Transformer for Dynamic Graph Modeling](https://mlsanity.com/paper/2401.14009/) (2024)
- [Improving Temporal Link Prediction via Temporal Walk Matrix Projection](https://mlsanity.com/paper/2410.04013/) (2024)
- [MDGNN: Multi-Relational Dynamic Graph Neural Network for Comprehensive and Dynamic Stock Investment Prediction](https://mlsanity.com/paper/2402.06633/) (2024)
- [AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-modal Alignment](https://mlsanity.com/paper/2412.00833/) (2024)
- [Co-Neighbor Encoding Schema: A Light-cost Structure Encoding Method for Dynamic Link Prediction](https://mlsanity.com/paper/2407.20871/) (2024)
- [Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck](https://mlsanity.com/paper/2406.13214/) (2024)
- [Towards Adaptive Neighborhood for Advancing Temporal Interaction Graph Modeling](https://mlsanity.com/paper/2406.11891/) (2024)
- [Practicable Black-box Evasion Attacks on Link Prediction in Dynamic Graphs -- A Graph Sequential Embedding Method](https://mlsanity.com/paper/2412.13134/) (2024)

## Built on by (most cited first, 3 of 3)

- [Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models](https://mlsanity.com/paper/2503.14411/) (2025)
- [Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective](https://mlsanity.com/paper/2608.18104/) (2026)
- [Transfer Learning for Edge Classification on Dynamic Text-Attributed Graphs](https://mlsanity.com/paper/2609.32849/) (2026)

## Abstract (arXiv)

Dynamic Text-Attributed Graphs (DyTAGs) are a novel graph paradigm that captures evolving temporal events (edges) alongside rich textual attributes. Existing studies can be broadly categorized into TGNN-driven and LLM-driven approaches, both of which encode textual attributes and temporal structures for DyTAG representation. We observe that DyTAGs inherently comprise three distinct modalities: temporal, textual, and structural, often exhibiting completely disjoint distributions. However, the first two modalities are largely overlooked by existing studies, leading to suboptimal performance. To address this, we propose MoMent, a multi-modal model that explicitly models, integrates, and aligns each modality to learn node representations for link prediction. Given the disjoint nature of the original modality distributions, we first construct modality-specific features and encode them using individual encoders to capture correlations across temporal patterns, semantic context, and local structures. Each encoder generates modality-specific tokens, which are then fused into comprehensive node representations with a theoretical guarantee. To avoid disjoint subspaces of these heterogeneous modalities, we propose a dual-domain alignment loss that first aligns their distributions globally and then fine-tunes coherence at the instance level. This enhances coherent representations from temporal, textual, and structural views. Extensive experiments across seven datasets show that MoMent achieves up to 17.28% accuracy improvement and up to 31x speed-up against eight baselines.