Search Results for author:
Found 44 papers, 26 papers with code
Large-Scale Spectral Graph Neural Networks via Laplacian Sparsification: Technical Report
To address the above challenges, we propose "Spectral Graph Neural Networks with Laplacian Sparsification (SGNN-LS)", a novel graph spectral sparsification method to approximate the propagation patterns of spectral GNNs.
SRAP-Agent: Simulating and Optimizing Scarce Resource Allocation Policy with LLM-based Agent
Public scarce resource allocation plays a crucial role in economics as it directly influences the efficiency and equity in society.
Fast Second-Order Online Kernel Learning through Incremental Matrix Sketching and Decomposition
Moreover, the absence of incremental updates to manage approximate kernel space causes these algorithms to perform poorly in adversarial environments and real-world streaming recommendation datasets.
Matrix Sketching in Bandits: Current Pitfalls and New Framework
To prevent this issue, we propose Dyadic Block Sketching, an innovative streaming matrix sketching approach that adaptively manages sketch size to constrain global spectral loss.
LLM-Based Multi-Agent Systems are Scalable Graph Generative Models
The structural properties of naturally arising social graphs are extensively studied to understand their evolution.
Scalable and Accurate Graph Reasoning with LLM-based Multi-Agents
Recent research has explored the use of Large Language Models (LLMs) for tackling complex graph reasoning tasks.
Rethinking the Expressiveness of GNNs: A Computational Model Perspective
Graph Neural Networks (GNNs) are extensively employed in graph machine learning, with considerable research focusing on their expressiveness.
S-MolSearch: 3D Semi-supervised Contrastive Learning for Bioactive Molecule Search
Virtual Screening is an essential technique in the early phases of drug discovery, aimed at identifying promising drug candidates from vast molecular libraries.
Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barrier
Remarkably, ScaleGUN accomplishes $(\epsilon,\delta)=(1, 10^{-4})$ certified unlearning on the billion-edge graph ogbn-papers100M in 20 seconds for a 5, 000 random edge removal request -- of which only 5 seconds are required for updating the node embeddings -- compared to 1. 91 hours for retraining and 1. 89 hours for re-propagation.
Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networks
In this paper, we systematically analyze the real dominant problem in deep GNNs and identify the issues that these GNNs towards addressing Over-smoothing essentially work on via empirical experiments and theoretical gradient analysis.
Towards Effective and Efficient Continual Pre-training of Large Language Models
To make the CPT approach more traceable, this paper presents a technical report for continually pre-training Llama-3 (8B), which significantly enhances the Chinese language ability and scientific reasoning ability of the backbone model.
Very Large-Scale Multi-Agent Simulation in AgentScope
Recent advances in large language models (LLMs) have opened new avenues for applying multi-agent systems in very large-scale simulations.
PolyFormer: Scalable Node-wise Filters via Polynomial Graph Transformer
However, many current methods focus on employing shared polynomial coefficients for all nodes, i. e., learning node-unified filters, which limits the filters' flexibility for node-level tasks.
YuLan: An Open-source Large Language Model
This paper presents the development of YuLan, a series of open-source LLMs with $12$ billion parameters.
PRICE: A Pretrained Model for Cross-Database Cardinality Estimation
It is generally applicable to any unseen new database to attain high estimation accuracy, while its preparation cost is as little as the basic one-dimensional histogram-based CardEst methods.
Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
In this paper, we pioneer the exploration of GIAs at the text level, presenting three novel attack designs that inject textual content into the graph.
Optimal Matrix Sketching over Sliding Windows
Matrix sketching, aimed at approximating a matrix $\boldsymbol{A} \in \mathbb{R}^{N\times d}$ consisting of vector streams of length $N$ with a smaller sketching matrix $\boldsymbol{B} \in \mathbb{R}^{\ell\times d}, \ell \ll N$, has garnered increasing attention in fields such as large-scale data analytics and machine learning.
A survey of dynamic graph neural networks
Graph neural networks (GNNs) have emerged as a powerful tool for effectively mining and learning from graph-structured data, with applications spanning numerous domains.
A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications
Geometric graph is a special kind of graph with geometric features, which is vital to model many scientific problems.
GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation
Vision Transformers (ViTs) have revolutionized the field of computer vision, yet their deployments on resource-constrained devices remain challenging due to high computational demands.
Ranked #197 on
Image Classification
on ImageNet
A Survey on Large Language Model based Autonomous Agents
In this paper, we present a comprehensive survey of these studies, delivering a systematic review of the field of LLM-based autonomous agents from a holistic perspective.
Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials
Furthermore, these methods cannot learn arbitrary valid heterogeneous graph filters within the spectral domain, which have limited expressiveness.
Ranked #6 on
Node Property Prediction
on ogbn-mag
Decoupled Graph Neural Networks for Large Dynamic Graphs
The experimental results demonstrate that our algorithm achieves state-of-the-art performance in both kinds of dynamic graphs.
LON-GNN: Spectral GNNs with Learnable Orthonormal Basis
In recent years, a plethora of spectral graph neural networks (GNN) methods have utilized polynomial basis with learnable coefficients to achieve top-tier performances on many node-level tasks.
Graph Neural Networks with Learnable and Optimal Polynomial Bases
Second, we examine the supposedly unsolvable definition of optimal polynomial basis from Wang & Zhang (2022) and propose a simple model, OptBasisGNN, which computes the optimal basis for a given graph structure and graph signal.
EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction
Predicting the binding sites of target proteins plays a fundamental role in drug discovery.
Do Deep Learning Methods Really Perform Better in Molecular Conformation Generation?
However, to our surprise, we design a simple and cheap algorithm (parameter-free) based on the traditional methods and find it is comparable to or even outperforms deep learning based MCG methods in the widely used GEOM-QM9 and GEOM-Drugs benchmarks.
Clenshaw Graph Neural Networks
Graph Convolutional Networks (GCNs), which use a message-passing paradigm with stacked convolution layers, are foundational methods for learning graph representations.
Predicting Protein-Ligand Binding Affinity via Joint Global-Local Interaction Modeling
The prediction of protein-ligand binding affinity is of great significance for discovering lead compounds in drug research.
Uni-Mol: A Universal 3D Molecular Representation Learning Framework
Uni-Mol is composed of two models with the same SE(3)-equivariant transformer architecture: a molecular pretraining model trained by 209M molecular conformations; a pocket pretraining model trained by 3M candidate protein pocket data.
Ranked #1 on
Molecular Property Prediction
on MUV
Instant Graph Neural Networks for Dynamic Graphs
With the development of numerous GNN variants, recent years have witnessed groundbreaking results in improving the scalability of GNNs to work on static graphs with millions of nodes.
EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks
Despite their extraordinary predictive accuracy, existing approaches, such as GCN and GPRGNN, are not robust in the face of homophily changes on test graphs, rendering these models vulnerable to graph structural attacks and with limited capacity in generalizing to graphs of varied homophily levels.
Preformer: Predictive Transformer with Multi-Scale Segment-wise Correlations for Long-Term Time Series Forecasting
In this way, if a key segment has a high correlation score with the query segment, its successive segment contributes more to the prediction of the query segment.
Learning to be a Statistician: Learned Estimator for Number of Distinct Values
We derive conditions of the learning framework under which the learned model is workload agnostic, in the sense that the model/estimator can be trained with synthetically generated training data, and then deployed into any data warehouse simply as, e. g., user-defined functions (UDFs), to offer efficient (within microseconds on CPU) and accurate NDV estimations for unseen tables and workloads.
Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited
GPR-GNN and BernNet demonstrate that the Monomial and Bernstein bases also outperform the Chebyshev basis in terms of learning the spectral graph convolutions.
MGNN: Graph Neural Networks Inspired by Distance Geometry Problem
As for spatial GNNs, models like Graph Isomorphism Networks (GIN) analyze their expressive power based on Graph Isomorphism Tests.
SCformer: Segment Correlation Transformer for Long Sequence Time Series Forecasting
Long-term time series forecasting is widely used in real-world applications such as financial investment, electricity management and production planning.
Coarformer: Transformer for large graph via graph coarsening
We get rid of these obstacles by exploiting the complementary natures of GNN and Transformer, and trade the fine-grained long-range information for the efficiency of Transformer.
BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
Many representative graph neural networks, e. g., GPR-GNN and ChebNet, approximate graph convolutions with graph spectral filters.
Graph Neural Networks Inspired by Classical Iterative Algorithms
Despite the recent success of graph neural networks (GNN), common architectures often exhibit significant limitations, including sensitivity to oversmoothing, long-range dependencies, and spurious edges, e. g., as can occur as a result of graph heterophily or adversarial attacks.
FlashP: An Analytical Pipeline for Real-time Forecasting of Time-Series Relational Data
Our scalable real-time forecasting system FlashP (Flash Prediction) is built based on this idea, with two major challenges to be resolved in this paper: first, we need to figure out how approximate aggregations affect the fitting of forecasting models, and forecasting results; and second, accordingly, what sampling algorithms we should use to obtain these approximate aggregations and how large the samples are.
Scalable Graph Neural Networks via Bidirectional Propagation
Most notably, GBP can deliver superior performance on a graph with over 60 million nodes and 1. 8 billion edges in less than half an hour on a single machine.
Simple and Deep Graph Convolutional Networks
We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: {\em Initial residual} and {\em Identity mapping}.
Scalable Graph Embeddings via Sparse Transpose Proximities
Based on the concept of transpose proximity, we design \strap, a factorization based graph embedding algorithm that achieves scalability and non-linearity simultaneously.
