Towards Neural Scaling Laws for Foundation Models on Temporal Graphs

• URL: http://arxiv.org/abs/2406.10426v2
• Date: Wed, 26 Jun 2024 19:26:58 GMT
• Title: Towards Neural Scaling Laws for Foundation Models on Temporal Graphs
• Authors: Razieh Shirzadkhani, Tran Gia Bao Ngo, Kiarash Shamsi, Shenyang Huang, Farimah Poursafaei, Poupak Azad, Reihaneh Rabbany, Baris Coskunuzer, Guillaume Rabusseau, Cuneyt Gurcan Akcora,
• Abstract summary: We present the Temporal Graph Scaling dataset, a large collection of temporal graphs consisting of eighty-four ERC20 token transaction networks. We evaluate the transferability of Temporal Graph Neural Networks (TGNNs) for the temporal graph property prediction task by pre-training. We find that the neural scaling law observed in NLP and Computer Vision also applies in temporal graph learning, where pre-training on greater number of networks leads to improved downstream performance.
• Score: 16.27236883013554
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The field of temporal graph learning aims to learn from evolving network data to forecast future interactions. Given a collection of observed temporal graphs, is it possible to predict the evolution of an unseen network from the same domain? To answer this question, we first present the Temporal Graph Scaling (TGS) dataset, a large collection of temporal graphs consisting of eighty-four ERC20 token transaction networks collected from 2017 to 2023. Next, we evaluate the transferability of Temporal Graph Neural Networks (TGNNs) for the temporal graph property prediction task by pre-training on a collection of up to sixty-four token transaction networks and then evaluating the downstream performance on twenty unseen token networks. We find that the neural scaling law observed in NLP and Computer Vision also applies in temporal graph learning, where pre-training on greater number of networks leads to improved downstream performance. To the best of our knowledge, this is the first empirical demonstration of the transferability of temporal graphs learning. On downstream token networks, the largest pre-trained model outperforms single model TGNNs on thirteen unseen test networks. Therefore, we believe that this is a promising first step towards building foundation models for temporal graphs.

Related papers

• NetFlowGen: Leveraging Generative Pre-training for Network Traffic Dynamics [72.95483148058378]
  We propose to pre-train a general-purpose machine learning model to capture traffic dynamics with only traffic data from NetFlow records. We address challenges such as unifying network feature representations, learning from large unlabeled traffic data volume, and testing on real downstream tasks in DDoS attack detection.
  arXiv  Detail & Related papers  (2024-12-30T00:47:49Z)
• Towards a graph-based foundation model for network traffic analysis [3.0558245652654907]
  Foundation models can grasp the complexities of network traffic dynamics and adapt to any specific task or environment with minimal fine-tuning. Previous approaches have used tokenized hex-level packet data. We propose a new, efficient graph-based alternative at the flow-level.
  arXiv  Detail & Related papers  (2024-09-12T15:04:34Z)
• FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective [48.00240550685946]
  Current state-of-the-art graph neural network (GNN)-based forecasting methods usually require both graph networks (e.g., GCN) and temporal networks (e.g., LSTM) to capture inter-series (spatial) dynamics and intra-series (temporal) dependencies, respectively. We propose a novel Fourier Graph Neural Network (FourierGNN) by stacking our proposed Fourier Graph Operator (FGO) to perform matrix multiplications in Fourier space. Our experiments on seven datasets have demonstrated superior performance with higher efficiency and fewer parameters compared with state-of-the-
  arXiv  Detail & Related papers  (2023-11-10T17:13:26Z)
• Sparsity exploitation via discovering graphical models in multi-variate time-series forecasting [1.2762298148425795]
  We propose a decoupled training method, which includes a graph generating module and a GNNs forecasting module. First, we use Graphical Lasso (or GraphLASSO) to directly exploit the sparsity pattern from data to build graph structures. Second, we fit these graph structures and the input data into a Graph Convolutional Recurrent Network (GCRN) to train a forecasting model.
  arXiv  Detail & Related papers  (2023-06-29T16:48:00Z)
• How neural networks learn to classify chaotic time series [77.34726150561087]
  We study the inner workings of neural networks trained to classify regular-versus-chaotic time series. We find that the relation between input periodicity and activation periodicity is key for the performance of LKCNN models.
  arXiv  Detail & Related papers  (2023-06-04T08:53:27Z)
• Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks [23.01100055999135]
  We present a scalable framework, namely SpikeNet, to efficiently capture the temporal and structural patterns of temporal graphs. As a low-power alternative to RNNs, SNNs explicitly model graph dynamics as spike trains of neuron populations. SpikeNet generalizes to a large temporal graph with significantly fewer parameters and computation overheads.
  arXiv  Detail & Related papers  (2022-08-15T09:22:15Z)
• The Multiple Subnetwork Hypothesis: Enabling Multidomain Learning by Isolating Task-Specific Subnetworks in Feedforward Neural Networks [0.0]
  We identify a methodology and network representational structure which allows a pruned network to employ previously unused weights to learn subsequent tasks. We show that networks trained using our approaches are able to learn multiple tasks, which may be related or unrelated, in parallel or in sequence without sacrificing performance on any task or exhibiting catastrophic forgetting.
  arXiv  Detail & Related papers  (2022-07-18T15:07:13Z)
• Spatial-Temporal Adaptive Graph Convolution with Attention Network for Traffic Forecasting [4.1700160312787125]
  We propose a novel network, Spatial-Temporal Adaptive graph convolution with Attention Network (STAAN) for traffic forecasting. Firstly, we adopt an adaptive dependency matrix instead of using a pre-defined matrix during GCN processing to infer the inter-dependencies among nodes. Secondly, we integrate PW-attention based on graph attention network which is designed for global dependency, and GCN as spatial block.
  arXiv  Detail & Related papers  (2022-06-07T09:08:35Z)
• Invertible Neural Networks for Graph Prediction [22.140275054568985]
  In this work, we address conditional generation using deep invertible neural networks. We adopt an end-to-end training approach since our objective is to address prediction and generation in the forward and backward processes at once.
  arXiv  Detail & Related papers  (2022-06-02T17:28:33Z)
• Neural Graph Matching for Pre-training Graph Neural Networks [72.32801428070749]
  Graph neural networks (GNNs) have been shown powerful capacity at modeling structural data. We present a novel Graph Matching based GNN Pre-Training framework, called GMPT. The proposed method can be applied to fully self-supervised pre-training and coarse-grained supervised pre-training.
  arXiv  Detail & Related papers  (2022-03-03T09:53:53Z)
• Time-Distributed Feature Learning in Network Traffic Classification for Internet of Things [3.1744605242927797]
  We propose a novel network data representation, treating the traffic data as a series of images. The network data is realized as a video stream to employ time-distributed (TD) feature learning. The experimental result shows that the TD feature learning the network classification performance elevates performance by 10%.
  arXiv  Detail & Related papers  (2021-09-29T20:01:40Z)
• Temporal Graph Network Embedding with Causal Anonymous Walks Representations [54.05212871508062]
  We propose a novel approach for dynamic network representation learning based on Temporal Graph Network. For evaluation, we provide a benchmark pipeline for the evaluation of temporal network embeddings. We show the applicability and superior performance of our model in the real-world downstream graph machine learning task provided by one of the top European banks.
  arXiv  Detail & Related papers  (2021-08-19T15:39:52Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)
• Graph-Based Neural Network Models with Multiple Self-Supervised Auxiliary Tasks [79.28094304325116]
  Graph Convolutional Networks are among the most promising approaches for capturing relationships among structured data points. We propose three novel self-supervised auxiliary tasks to train graph-based neural network models in a multi-task fashion.
  arXiv  Detail & Related papers  (2020-11-14T11:09:51Z)
• Unsupervised Transfer Learning for Spatiotemporal Predictive Networks [90.67309545798224]
  We study how to transfer knowledge from a zoo of unsupervisedly learned models towards another network. Our motivation is that models are expected to understand complex dynamics from different sources. Our approach yields significant improvements on three benchmarks fortemporal prediction, and benefits the target even from less relevant ones.
  arXiv  Detail & Related papers  (2020-09-24T15:40:55Z)
• Towards Deeper Graph Neural Networks [63.46470695525957]
  Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations. Several recent studies attribute this performance deterioration to the over-smoothing issue. We propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields.
  arXiv  Detail & Related papers  (2020-07-18T01:11:14Z)
• GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training [62.73470368851127]
  Graph representation learning has emerged as a powerful technique for addressing real-world problems. We design Graph Contrastive Coding -- a self-supervised graph neural network pre-training framework. We conduct experiments on three graph learning tasks and ten graph datasets.
  arXiv  Detail & Related papers  (2020-06-17T16:18:35Z)
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction [69.1473775184952]
  We introduce a realistic problem of few-shot out-of-graph link prediction. We tackle this problem with a novel transductive meta-learning framework. We validate our model on multiple benchmark datasets for knowledge graph completion and drug-drug interaction prediction.
  arXiv  Detail & Related papers  (2020-06-11T17:42:46Z)
• Modeling Dynamic Heterogeneous Network for Link Prediction using Hierarchical Attention with Temporal RNN [16.362525151483084]
  We propose a novel dynamic heterogeneous network embedding method, termed as DyHATR. It uses hierarchical attention to learn heterogeneous information and incorporates recurrent neural networks with temporal attention to capture evolutionary patterns. We benchmark our method on four real-world datasets for the task of link prediction.
  arXiv  Detail & Related papers  (2020-04-01T17:16:47Z)
• Curriculum By Smoothing [52.08553521577014]
  Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. We propose an elegant curriculum based scheme that smoothes the feature embedding of a CNN using anti-aliasing or low-pass filters. As the amount of information in the feature maps increases during training, the network is able to progressively learn better representations of the data.
  arXiv  Detail & Related papers  (2020-03-03T07:27:44Z)

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.