Towards Practical Large-scale Dynamical Heterogeneous Graph Embedding: Cold-start Resilient Recommendation

• URL: http://arxiv.org/abs/2512.13120v1
• Date: Mon, 15 Dec 2025 09:19:23 GMT
• Title: Towards Practical Large-scale Dynamical Heterogeneous Graph Embedding: Cold-start Resilient Recommendation
• Abstract summary: This paper introduces a practical, two-stage solution that balances deep graph representation with low-latency incremental updates.<n>Our framework combines HetSGFormer, a scalable graph transformer for static learning, with Incremental Locally Linear Embedding (ILLE), a lightweight, CPU-based algorithm for real-time updates.
• Score: 45.70605679051105
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deploying dynamic heterogeneous graph embeddings in production faces key challenges of scalability, data freshness, and cold-start. This paper introduces a practical, two-stage solution that balances deep graph representation with low-latency incremental updates. Our framework combines HetSGFormer, a scalable graph transformer for static learning, with Incremental Locally Linear Embedding (ILLE), a lightweight, CPU-based algorithm for real-time updates. HetSGFormer captures global structure with linear scalability, while ILLE provides rapid, targeted updates to incorporate new data, thus avoiding costly full retraining. This dual approach is cold-start resilient, leveraging the graph to create meaningful embeddings from sparse data. On billion-scale graphs, A/B tests show HetSGFormer achieved up to a 6.11% lift in Advertiser Value over previous methods, while the ILLE module added another 3.22% lift and improved embedding refresh timeliness by 83.2%. Our work provides a validated framework for deploying dynamic graph learning in production environments.

Related papers

• Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphs [43.39867023055097]
  We propose SG-JEPA, a joint spiking embedding predictive architecture for large-scale dynamic graphs.<n> SG-JEPA partitions nodes into context and target sets along the temporal dimension to learn embeddings that are predictive of each other.<n>Experiments demonstrate that SG-JEPA achieves competitive or even superior performance over discriminative baselines on node classification.
  arXiv  Detail & Related papers  (2026-07-20T18:02:04Z)
• 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)
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning [50.40400074353263]
  Graph Neural Networks (GNNs) are powerful tools for precessing relational data but often struggle to generalize to unseen graphs.<n>We introduce textbfGraph textbfIn-context textbfL textbfTransformer (GILT), a framework built on an LLM-free and tuning-free architecture.
  arXiv  Detail & Related papers  (2025-10-06T08:09:15Z)
• EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora [20.890240791042302]
  Graph-based Retrieval-Augmented Generation (Graph-RAG) enhances large language models (LLMs) by structuring retrieval over an external corpus.<n>We introduce EraRAG, a novel multi-layered Graph-RAG framework that supports efficient and scalable dynamic updates.<n>Our method leverages hyperplane-based Locality-Sensitive Hashing (LSH) to partition and organize the original corpus into hierarchical graph structures.
  arXiv  Detail & Related papers  (2025-06-26T03:01:33Z)
• Dynamic Graph Condensation [40.099854631984556]
  temporal extension in dynamic graphs poses significant data efficiency challenges.<n>We propose DyGC, a framework that condenses the real dynamic graph into a compact version.<n>Our method retains up to 96.2% DGNN performance with only 0.5% of the original graph size, and achieves up to 1846 times training speedup.
  arXiv  Detail & Related papers  (2025-06-16T05:11:29Z)
• Scalable Graph Generative Modeling via Substructure Sequences [50.32639806800683]
  We introduce Generative Graph Pattern Machine (G$2$PM), a generative Transformer pre-training framework for graphs.<n>G$2$PM represents graph instances (nodes, edges, or entire graphs) as sequences of substructures.<n>It employs generative pre-training over the sequences to learn generalizable and transferable representations.
  arXiv  Detail & Related papers  (2025-05-22T02:16:34Z)
• RGL: A Graph-Centric, Modular Framework for Efficient Retrieval-Augmented Generation on Graphs [58.10503898336799]
  We introduce the RAG-on-Graphs Library (RGL), a modular framework that seamlessly integrates the complete RAG pipeline.<n>RGL addresses key challenges by supporting a variety of graph formats and integrating optimized implementations for essential components.<n>Our evaluations demonstrate that RGL not only accelerates the prototyping process but also enhances the performance and applicability of graph-based RAG systems.
  arXiv  Detail & Related papers  (2025-03-25T03:21:48Z)
• Instant Representation Learning for Recommendation over Large Dynamic Graphs [29.41179019520622]
  We propose SUPA, a novel graph neural network for dynamic multiplex heterogeneous graphs. For each new edge, SUPA samples an influenced subgraph, updates the representations of the two interactive nodes, and propagates the interaction information to the sampled subgraph. To train SUPA incrementally online, we propose InsLearn, an efficient workflow for single-pass training of large dynamic graphs.
  arXiv  Detail & Related papers  (2023-05-22T15:36:10Z)
• EGRC-Net: Embedding-induced Graph Refinement Clustering Network [66.44293190793294]
  We propose a novel graph clustering network called Embedding-Induced Graph Refinement Clustering Network (EGRC-Net) EGRC-Net effectively utilizes the learned embedding to adaptively refine the initial graph and enhance the clustering performance. Our proposed methods consistently outperform several state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-11-19T09:08:43Z)
• Instant Graph Neural Networks for Dynamic Graphs [18.916632816065935]
  We propose Instant Graph Neural Network (InstantGNN), an incremental approach for the graph representation matrix of dynamic graphs. Our method avoids time-consuming, repetitive computations and allows instant updates on the representation and instant predictions. Our model achieves state-of-the-art accuracy while having orders-of-magnitude higher efficiency than existing methods.
  arXiv  Detail & Related papers  (2022-06-03T03:27:42Z)
• Causal Incremental Graph Convolution for Recommender System Retraining [89.25922726558875]
  Real-world recommender system needs to be regularly retrained to keep with the new data. In this work, we consider how to efficiently retrain graph convolution network (GCN) based recommender models.
  arXiv  Detail & Related papers  (2021-08-16T04:20:09Z)
• Robust Optimization as Data Augmentation for Large-scale Graphs [117.2376815614148]
  We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training. FLAG is a general-purpose approach for graph data, which universally works in node classification, link prediction, and graph classification tasks.
  arXiv  Detail & Related papers  (2020-10-19T21:51:47Z)

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.