Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJune 2024
Revisiting Local Computation of PageRank: Simple and Optimal
STOC 2024: Proceedings of the 56th Annual ACM Symposium on Theory of ComputingJune 2024, Pages 911–922https://doi.org/10.1145/3618260.3649661We revisit ApproxContributions, the classic local graph exploration algorithm proposed by Andersen, Borgs, Chayes, Hopcroft, Mirrokni, and Teng (WAW ’07, Internet Math. ’08) for computing an є-approximation of the PageRank contribution vector for a ...
- research-articleJune 2024
BernNet: learning arbitrary graph spectral filters via bernstein approximation
NIPS '21: Proceedings of the 35th International Conference on Neural Information Processing SystemsDecember 2021, Article No.: 1091, Pages 14239–14251Many representative graph neural networks, e.g., GPR-GNN and ChebNet, approximate graph convolutions with graph spectral filters. However, existing work either applies predefined filter weights or learns them without necessary constraints, which may lead ...
- research-articleMay 2024
Learning-based Property Estimation with Polynomials
Proceedings of the ACM on Management of Data (PACMMOD), Volume 2, Issue 3Article No.: 148, Pages 1–27https://doi.org/10.1145/3654994The problem of estimating data properties using sampling frequency histograms has attracted extensive interest in the area of databases. The properties include the number of distinct values (NDV), entropy, and so on. In the field of databases, property ...
- research-articleMay 2024
Exploring Neural Scaling Law and Data Pruning Methods For Node Classification on Large-scale Graphs
WWW '24: Proceedings of the ACM on Web Conference 2024May 2024, Pages 780–791https://doi.org/10.1145/3589334.3645571Recently, how the model performance scales with the training sample size has been extensively studied for large models on vision and language related domains. Nevertheless, the ubiquitous node classification tasks on web-scale graphs were ignored, where ...
- research-articleMay 2024
Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials
WWW '24: Proceedings of the ACM on Web Conference 2024May 2024, Pages 685–696https://doi.org/10.1145/3589334.3645515Heterogeneous Graph Neural Networks (HGNNs) have gained significant popularity in various heterogeneous graph learning tasks. However, most existing HGNNs rely on spatial domain-based methods to aggregate information, i.e., manually selected meta-paths ...
-
- research-articleApril 2024
Convolutional neural networks on graphs with chebyshev approximation, revisited
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsNovember 2022, Article No.: 527, Pages 7264–7276Designing spectral convolutional networks is a challenging problem in graph learning. ChebNet, one of the early attempts, approximates the spectral graph convolutions using Chebyshev polynomials. GCN simplifies ChebNet by utilizing only the first two ...
- research-articleApril 2024
EvenNet: ignoring odd-hop neighbors improves robustness of graph neural networks
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsNovember 2022, Article No.: 339, Pages 4694–4706Graph Neural Networks (GNNs) have received extensive research attention for their promising performance in graph machine learning. Despite their extraordinary predictive accuracy, existing approaches, such as GCN and GPRGNN, are not robust in the face of ...
- review-articleMarch 2024
A survey on large language model based autonomous agents
- Lei Wang,
- Zeyu Zhang,
- Hao Yang,
- Jingsen Zhang,
- Zhiyuan Chen,
- Jiakai Tang,
- Xu Chen,
- Yankai Lin,
- Wayne Xin Zhao,
- Zhewei Wei,
- Jirong Wen,
- Chen Ma,
- Xueyang Feng
Frontiers of Computer Science: Selected Publications from Chinese Universities (FCS), Volume 18, Issue 6Dec 2024https://doi.org/10.1007/s11704-024-40231-1AbstractAutonomous agents have long been a research focus in academic and industry communities. Previous research often focuses on training agents with limited knowledge within isolated environments, which diverges significantly from human learning ...
- research-articleDecember 2023
Index-free triangle-based graph local clustering
Frontiers of Computer Science: Selected Publications from Chinese Universities (FCS), Volume 18, Issue 3Jun 2024https://doi.org/10.1007/s11704-023-2768-7AbstractMotif-based graph local clustering (MGLC) is a popular method for graph mining tasks due to its various applications. However, the traditional two-phase approach of precomputing motif weights before performing local clustering loses locality and ...
- research-articleOctober 2023
Enabling Efficient Random Access to Hierarchically Compressed Text Data on Diverse GPU Platforms
- Yihua Hu,
- Feng Zhang,
- Yifei Xia,
- Zhiming Yao,
- Letian Zeng,
- Haipeng Ding,
- Zhewei Wei,
- Xiao Zhang,
- Jidong Zhai,
- Xiaoyong Du,
- Siqi Ma
IEEE Transactions on Parallel and Distributed Systems (TPDS), Volume 34, Issue 10Oct. 2023, Pages 2699–2717https://doi.org/10.1109/TPDS.2023.3294341The tremendous computing capacity of GPU offers significant potential in processing hierarchically compressed text data without decompression. However, current GPU techniques offer only traversal-based text data analytics; random access is exceedingly ...
- research-articleAugust 2023
Optimal Dynamic Subset Sampling: Theory and Applications
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningAugust 2023, Pages 3116–3127https://doi.org/10.1145/3580305.3599458We study the fundamental problem of sampling independent events, called subset sampling. Specifically, consider a set of n distinct events S=x1, …, xn, in which each event xi has an associated probability p(xi). The subset sampling problem aims to ...
- research-articleAugust 2023
MGNN: Graph Neural Networks Inspired by Distance Geometry Problem
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningAugust 2023, Pages 335–347https://doi.org/10.1145/3580305.3599431Graph Neural Networks (GNNs) have emerged as a prominent research topic in the field of machine learning. Existing GNN models are commonly categorized into two types: spectral GNNs, which are designed based on polynomial graph filters, and spatial GNNs, ...
- research-articleAugust 2023
Clenshaw Graph Neural Networks
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningAugust 2023, Pages 614–625https://doi.org/10.1145/3580305.3599275Graph Convolutional Networks (GCNs), which use a message-passing paradigm with stacked convolution layers, are foundational spatial methods for learning graph representations. Polynomial filters, which have an advantage on heterophilous graphs, are ...
- research-articleJuly 2023
Graph neural networks with learnable and optimal polynomial bases
ICML'23: Proceedings of the 40th International Conference on Machine LearningJuly 2023, Article No.: 485, Pages 12077–12097Polynomial filters, a kind of Graph Neural Networks, typically use a predetermined polynomial basis and learn the coefficients from the training data. It has been observed that the effectiveness of the model is highly dependent on the property of the ...
Estimating Single-Node PageRank in Õ (min{dt, √m}) Time
Proceedings of the VLDB Endowment (PVLDB), Volume 16, Issue 11Pages 2949–2961https://doi.org/10.14778/3611479.3611500PageRank is a famous measure of graph centrality that has numerous applications in practice. The problem of computing a single node's PageRank has been the subject of extensive research over a decade. However, existing methods still incur large time ...
- research-articleMay 2023
Personalized PageRank on Evolving Graphs with an Incremental Index-Update Scheme
Proceedings of the ACM on Management of Data (PACMMOD), Volume 1, Issue 1Article No.: 25, Pages 1–26https://doi.org/10.1145/3588705\em Personalized PageRank (PPR) stands as a fundamental proximity measure in graph mining. Given an input graph G with the probability of decay α, a source node s and a target node t, the PPR score π(s,t) of target t with respect to source s is the ...
Decoupled Graph Neural Networks for Large Dynamic Graphs
Proceedings of the VLDB Endowment (PVLDB), Volume 16, Issue 9Pages 2239–2247https://doi.org/10.14778/3598581.3598595Real-world graphs, such as social networks, financial transactions, and recommendation systems, often demonstrate dynamic behavior. This phenomenon, known as graph stream, involves the dynamic changes of nodes and the emergence and disappearance of ...
Optimizing random access to hierarchically-compressed data on GPU
SC '22: Proceedings of the International Conference on High Performance Computing, Networking, Storage and AnalysisNovember 2022, Article No.: 18, Pages 1–15GPU's powerful computational capacity holds great potentials for processing hierarchically-compressed data without decompression in data science domain. Unfortunately, existing GPU approaches offer only traversal-based data analytics; random access is ...
- research-articleOctober 2022
MGMAE: Molecular Representation Learning by Reconstructing Heterogeneous Graphs with A High Mask Ratio
CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge ManagementOctober 2022, Pages 509–519https://doi.org/10.1145/3511808.3557395Masked autoencoder (MAE), as an effective self-supervised learner for computer vision and natural language processing, has been recently applied to molecule representation learning. In this paper, we identify two issues in applying MAE to pre-train ...
Approximating probabilistic group steiner trees in graphs
Proceedings of the VLDB Endowment (PVLDB), Volume 16, Issue 2Pages 343–355https://doi.org/10.14778/3565816.3565834Consider an edge-weighted graph, and a number of properties of interests (PoIs). Each vertex has a probability of exhibiting each PoI. The joint probability that a set of vertices exhibits a PoI is the probability that this set contains at least one ...