LGA: LLM-GNN Aggregation for Temporal Evolution Attribute Graph Prediction (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current methods focus on 1-hop neighborhood aggregation, lacking capability to capture complex structural interactions. |
| Approach: | They propose a framework that integrates structural information into attribute embeddings through an attribute embedded loss. |
| Outcome: | The proposed framework shows significant improvements over existing methods on real-world datasets. |
Similar Papers
Holistic Prediction on a Time-Evolving Attributed Graph (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for predicting future links, nodes, and attributes of time-evolving attributed graphs are not accurate. |
| Approach: | They propose a framework that predicts node attributes and topology changes such as appearance and disappearance of links and the emergence and loss of nodes. |
| Outcome: | The proposed framework improves on existing methods that assume that each link, node, and attribute prediction is independent and fails to predict new nodes that were not observed in the past. |
Marrying LLMs with Dynamic Forecasting: A Graph Mixture-of-expert Perspective (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent data-driven approaches often use graph neural networks (GNNs) to learn relationships in dynamical systems. |
| Approach: | They propose a framework which leverages large language models to enhance generalization capabilities of dynamical system modeling. |
| Outcome: | The proposed framework improves on existing methods and compares to baselines. |
STK-Adapter: Incorporating Evolving Graph and Event Chain for Temporal Knowledge Graph Extrapolation (2026.acl-long)
Copied to clipboard
Shuyuan Zhao, Wei Chen, Weijie Zhang, Xinrui Hou, Junfeng Shen, Boyan Shi, Shengnan Guo, Youfang Lin, Huaiyu Wan
| Challenge: | Temporal Knowledge Graphs (TKGs) store dynamic facts in the real world. |
| Approach: | They propose a Spatial-Temporal Knowledge Adapter which integrates the evolving graph encoder and the LLM to facilitate TKG reasoning. |
| Outcome: | The proposed method outperforms state-of-the-art methods on benchmark datasets and exhibits strong generalization capabilities in cross-dataset task. |
Exploring the Potential of Large Language Models for Heterophilic Graphs (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing approaches for heterophilic graphs overlook rich textual data associated with nodes, which could unlock deeper insights into their heterophilistic contexts. |
| Approach: | They propose a two-stage framework to enhance node classification on heterophilic graphs by leveraging open-world knowledge encoded by large language models. |
| Outcome: | The proposed framework can be used to better characterize heterophilic graphs, where neighboring nodes often exhibit different labels. |
An LLM-Embedding Semantic Adaptation Network for Post-level Semantic Drift Evaluation (2026.findings-acl)
Copied to clipboard
| Challenge: | Evaluating semantic drift is essential for understanding discourse evolution and opinion formation in online discussions. |
| Approach: | They propose an LLM-embedding Semantic Adaptation Network to evaluate semantic drift . they use an LRU module, an LEM-Embedding graph convolutional network module and an adaptive fusion module to integrate features from event related posts. |
| Outcome: | The proposed model achieves state-of-the-art performance on the semantic drift evaluation task compared to baseline models. |
TimeSAF: Towards LLM-Guided Semantic Asynchronous Fusion for Time Series Forecasting (2026.acl-long)
Copied to clipboard
| Challenge: | Existing time series forecasting methods use a deep synchronous fusion strategy . high-level abstract semantics are inappropriately entangled with low-level temporal dynamics . |
| Approach: | They propose a framework based on hierarchical asynchronous fusion that decouples unimodal feature learning from cross-modal interaction. |
| Outcome: | The proposed framework outperforms state-of-the-art approaches on long-term forecasting benchmarks. |
Compressing LLM Knowledge into Graph Representations for Text-attributed Graphs Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing GNN-LLM approaches use large language models at inference time for processing text attributes, resulting in costly deployment. |
| Approach: | They propose a framework that internalizes LLM knowledge within graph models and supports inference-efficient TAG learning. |
| Outcome: | The proposed framework internalizes LLM knowledge within graph models and supports inference-efficient TAG learning. |
SRM-LLM: Semantic Relationship Mining with LLMs for Temporal Knowledge Graph Extrapolation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for temporal knowledge graph extrapolation neglect the complex semantic relationships between relations when modeling their dynamic evolution. |
| Approach: | They propose a method for extracting semantic relationships to achieve TKG extrapolation . they use large language models to analyze the types of relations in TKGs . |
| Outcome: | The proposed method improves on five TKG datasets and shows performance gains. |
G2S: A General-to-Specific Learning Framework for Temporal Knowledge Graph Forecasting with Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have introduced Large Language Models (LLMs) for this task to enhance the models’ generalization abilities. |
| Approach: | They propose a General-to-Specific learning framework that disentangles the learning processes of two kinds of knowledge in a temporal temporal structure. |
| Outcome: | The proposed framework disentangles the learning processes of the above two kinds of knowledge and improves their generalization abilities. |
Natural Evolution-based Dual-Level Aggregation for Temporal Knowledge Graph Reasoning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models ignore asynchronous characteristics of event evolution, resulting in suboptimal performance. |
| Approach: | They propose a Natural Evolution-based Dual-level Aggregation framework for TKG reasoning that incorporates asynchronous characteristics of event evolution into the model. |
| Outcome: | The proposed model incorporates the asynchronous characteristics of event evolution for representation computation, thus improving prediction performance. |