EvoFormer: Learning Dynamic Graph-Level Representations with Structural and Temporal Bias Correction

• URL: http://arxiv.org/abs/2508.15378v1
• Date: Thu, 21 Aug 2025 09:19:54 GMT
• Title: EvoFormer: Learning Dynamic Graph-Level Representations with Structural and Temporal Bias Correction
• Abstract summary: Dynamic graph-level embedding aims to capture structural evolution in networks.<n>Existing methods face two critical yet under-explored issues: Structural Visit Bias and Abrupt Evolution Blindness.<n>We propose EvoFormer, an evolution-aware Transformer framework tailored for dynamic graph-level representation learning.
• Score: 16.798673711008906
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dynamic graph-level embedding aims to capture structural evolution in networks, which is essential for modeling real-world scenarios. However, existing methods face two critical yet under-explored issues: Structural Visit Bias, where random walk sampling disproportionately emphasizes high-degree nodes, leading to redundant and noisy structural representations; and Abrupt Evolution Blindness, the failure to effectively detect sudden structural changes due to rigid or overly simplistic temporal modeling strategies, resulting in inconsistent temporal embeddings. To overcome these challenges, we propose EvoFormer, an evolution-aware Transformer framework tailored for dynamic graph-level representation learning. To mitigate Structural Visit Bias, EvoFormer introduces a Structure-Aware Transformer Module that incorporates positional encoding based on node structural roles, allowing the model to globally differentiate and accurately represent node structures. To overcome Abrupt Evolution Blindness, EvoFormer employs an Evolution-Sensitive Temporal Module, which explicitly models temporal evolution through a sequential three-step strategy: (I) Random Walk Timestamp Classification, generating initial timestamp-aware graph-level embeddings; (II) Graph-Level Temporal Segmentation, partitioning the graph stream into segments reflecting structurally coherent periods; and (III) Segment-Aware Temporal Self-Attention combined with an Edge Evolution Prediction task, enabling the model to precisely capture segment boundaries and perceive structural evolution trends, effectively adapting to rapid temporal shifts. Extensive evaluations on five benchmark datasets confirm that EvoFormer achieves state-of-the-art performance in graph similarity ranking, temporal anomaly detection, and temporal segmentation tasks, validating its effectiveness in correcting structural and temporal biases.

Related papers

• TTGBench: Benchmarking Topological Evolution and Semantic Drift in Text-attributed Temporal Graphs [24.36945438269572]
  Temporal graph learning models the evolution of dynamic systems, where both structural interactions and semantic states change over time.<n>We introduce textbfTTGBench, a new benchmark that jointly evaluates structural and semantic evolution.<n>We conduct a comprehensive evaluation of 17 state-of-the-art methods across Temporal Graph Neural Networks (TGNNs) and Large Language Model (LLM)-based paradigms.
  arXiv  Detail & Related papers  (2026-09-08T04:19:11Z)
• Temporal Memory-Aware Online Test-Time Adaptation on Dynamic Graphs [52.31268996286955]
  Test-time adaptation (TTA) on graphs aims to adapt a graph neural network (GNN) that is well-trained on the training graph to the test graph.<n>We propose a novel framework of temporal memory-aware Online Test-Time Adaptation on Dynamic Graphs, named DGOTTA, to effectively adapt well-trained DGNNs during test time.
  arXiv  Detail & Related papers  (2026-08-28T05:41:39Z)
• PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphs [97.88691137307723]
  We propose PromptDyG, a novel framework that leverages unsupervised test-time Prompt adaptation for Dynamic Graph learning under a live-update online setting.<n>We show theoretically that this unsupervised prompt adaptation can guarantee a larger similarity margin between positive and negative pairs, facilitating more accurate dynamic predictions.
  arXiv  Detail & Related papers  (2026-06-22T06:54:02Z)
• Graph2TS: Structure-Controlled Time Series Generation via Quantile-Graph VAEs [1.0499611180329804]
  We propose a structure-residual perspective on time-series generation, viewing temporal data as the combination of a structural backbone and residual dynamics.<n>By conditioning generation on structure rather than labels or metadata, the model preserves global temporal organization while enabling controlled variation.<n> Experiments on diverse datasets, including sunspot, electricity load, ECG, and EEG signals, demonstrate improved distributional fidelity, temporal alignment, and representativeness compared to diffusion- and GAN-based baselines.
  arXiv  Detail & Related papers  (2026-03-20T14:12:11Z)
• Pruning for Generalization: A Transfer-Oriented Spatiotemporal Graph Framework [0.6435984242701042]
  We propose TL-GPSGNT to improve graph-based time series forecasting models.<n>We use information-theoretic and correlation-based criteria to extract structurally informative subgraphs.<n>We show that TL-GPSGNT consistently outperforms baselines in low-data transfer scenarios.
  arXiv  Detail & Related papers  (2026-02-04T02:41:29Z)
• Temporal Graph Pattern Machine [17.352525018007473]
  Temporal Graph Pattern Machine (TGPM) conceptualizes each interaction as an interaction patch synthesized via temporally-biased random walks.<n>TGPM consistently achieves state-of-the-art performance in both transductive and inductive link prediction.
  arXiv  Detail & Related papers  (2026-01-30T01:46:13Z)
• Kuramoto Orientation Diffusion Models [67.0711709825854]
  Orientation-rich images, such as fingerprints and textures, often exhibit coherent angular patterns.<n>Motivated by the role of phase synchronization in biological systems, we propose a score-based generative model.<n>We implement competitive results on general image benchmarks and significantly improves generation quality on orientation-dense datasets like fingerprints and textures.
  arXiv  Detail & Related papers  (2025-09-18T18:18:49Z)
• Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains [50.66049136093248]
  We develop a time-aware structural causal model (SCM) that incorporates dynamic causal factors and the causal mechanism drifts.<n>We show that our method can yield the optimal causal predictor for each time domain.<n>Results on both synthetic and real-world datasets exhibit that SYNC can achieve superior temporal generalization performance.
  arXiv  Detail & Related papers  (2025-06-21T14:05:37Z)
• STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization [34.53308463024231]
  We propose an innovative Spatio-Temporal Retrieval-Augmented Pattern Learning framework, STRAP.<n>During inference, STRAP retrieves relevant patterns from this library based on similarity to the current input and injects them into the model via a plug-and-play prompting mechanism.<n>Experiments across multiple real-world streaming graph datasets show that STRAP consistently outperforms state-of-the-art STGNN baselines on STOOD tasks.
  arXiv  Detail & Related papers  (2025-05-26T06:11:05Z)
• Structural-Temporal Coupling Anomaly Detection with Dynamic Graph Transformer [41.16574023720132]
  We propose a structural-temporal coupling anomaly detection architecture with a dynamic graph transformer model.<n>Specifically, we introduce structural and temporal features from two integration levels to provide anomaly-aware graph evolutionary patterns.
  arXiv  Detail & Related papers  (2025-05-13T08:10:41Z)
• Dynamic Graph Representation Learning via Edge Temporal States Modeling and Structure-reinforced Transformer [5.093187534912688]
  We introduce the Recurrent Structure-reinforced Graph Transformer (RSGT), a novel framework for dynamic graph representation learning. RSGT captures temporal node representations encoding both graph topology and evolving dynamics through a recurrent learning paradigm. We show RSGT's superior performance in discrete dynamic graph representation learning, consistently outperforming existing methods in dynamic link prediction tasks.
  arXiv  Detail & Related papers  (2023-04-20T04:12:50Z)
• EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning [92.71579608528907]
  This paper aims to design an easy-to-use pipeline (termed as EasyDGL) composed of three key modules with both strong ability fitting and interpretability. EasyDGL can effectively quantify the predictive power of frequency content that a model learn from the evolving graph data.
  arXiv  Detail & Related papers  (2023-03-22T06:35:08Z)
• Self-Supervised Temporal Graph learning with Temporal and Structural Intensity Alignment [53.72873672076391]
  Temporal graph learning aims to generate high-quality representations for graph-based tasks with dynamic information. We propose a self-supervised method called S2T for temporal graph learning, which extracts both temporal and structural information. S2T achieves at most 10.13% performance improvement compared with the state-of-the-art competitors on several datasets.
  arXiv  Detail & Related papers  (2023-02-15T06:36:04Z)
• Time-aware Dynamic Graph Embedding for Asynchronous Structural Evolution [60.695162101159134]
  Existing works merely view a dynamic graph as a sequence of changes. We formulate dynamic graphs as temporal edge sequences associated with joining time of. vertex and timespan of edges. A time-aware Transformer is proposed to embed. vertex' dynamic connections and ToEs into the learned. vertex representations.
  arXiv  Detail & Related papers  (2022-07-01T15:32:56Z)
• Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective [72.55093886515824]
  We introduce a causal formalism of motion forecasting, which casts the problem as a dynamic process with three groups of latent variables. We devise a modular architecture that factorizes the representations of invariant mechanisms and style confounders to approximate a causal graph. Experiment results on synthetic and real datasets show that our three proposed components significantly improve the robustness and reusability of the learned motion representations.
  arXiv  Detail & Related papers  (2021-11-29T18:59:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.