Search Results for author:
Found 40 papers, 30 papers with code
Distributed Methods for High-dimensional and Large-scale Tensor Factorization
Can we process it on commodity computers with limited memory?
Why You Should Charge Your Friends for Borrowing Your Stuff
We consider goods that can be shared with k-hop neighbors (i. e., the set of nodes within k hops from an owner) on a social network.
WRS: Waiting Room Sampling for Accurate Triangle Counting in Real Graph Streams
WRS exploits the temporal locality by always storing the most recent edges, which future edges are more likely to form triangles with, in the waiting room, while it uses reservoir sampling for the remaining edges.
Databases Data Structures and Algorithms H.2.8; G.2.2
Out-of-Core and Distributed Algorithms for Dense Subtensor Mining
Can we detect it when data are too large to fit in memory or even on a disk?
Databases Distributed, Parallel, and Cluster Computing Social and Information Networks H.2.8
MIDAS: Microcluster-Based Detector of Anomalies in Edge Streams
Given a stream of graph edges from a dynamic graph, how can we assign anomaly scores to edges in an online manner, for the purpose of detecting unusual behavior, using constant time and memory?
Ranked #1 on
Anomaly Detection in Edge Streams
on Darpa
MONSTOR: An Inductive Approach for Estimating and Maximizing Influence over Unseen Networks
In this work, we present an inductive machine learning method, called Monte Carlo Simulator (MONSTOR), for estimating the influence of given seed nodes in social networks unseen during training.
How Much and When Do We Need Higher-order Information in Hypergraphs? A Case Study on Hyperedge Prediction
Hypergraphs provide a natural way of representing group relations, whose complexity motivates an extensive array of prior work to adopt some form of abstraction and simplification of higher-order interactions.
Hypergraph Motifs: Concepts, Algorithms, and Discoveries
(Q3) how can we identify domains which hypergraphs are from?
Social and Information Networks Databases Data Structures and Algorithms H.2.8
SSumM: Sparse Summarization of Massive Graphs
SSumM not only merges nodes together but also sparsifies the summary graph, and the two strategies are carefully balanced based on the minimum description length principle.
Databases Social and Information Networks H.2.8
Structural Patterns and Generative Models of Real-world Hypergraphs
Graphs have been utilized as a powerful tool to model pairwise relationships between people or objects.
Social and Information Networks Physics and Society
Evolution of Real-world Hypergraphs: Patterns and Models without Oracles
What kind of macroscopic structural and dynamical patterns can we observe in real-world hypergraphs?
Social and Information Networks
Real-Time Anomaly Detection in Edge Streams
Given a stream of graph edges from a dynamic graph, how can we assign anomaly scores to edges in an online manner, for the purpose of detecting unusual behavior, using constant time and memory?
Summarizing graphs using configuration model
As a solution, graph summarization, which aims to find a compact representation that preserves the important properties of a given graph, has received much attention, and numerous algorithms have been developed for it.
Social and Information Networks
Two-stage Training of Graph Neural Networks for Graph Classification
By adapting five GNN models to our method, we demonstrate the consistent improvement in accuracy and utilization of each GNN's allocated capacity over the original training method of each model up to 5. 4\% points in 12 datasets.
Fast and Accurate Anomaly Detection in Dynamic Graphs with a Two-Pronged Approach
This allows us to detect sudden changes in the importance of any node.
Robust Factorization of Real-world Tensor Streams with Patterns, Missing Values, and Outliers
Consider multiple seasonal time series being collected in real-time, in the form of a tensor stream.
SliceNStitch: Continuous CP Decomposition of Sparse Tensor Streams
SLICENSTITCH changes the starting point of each period adaptively, based on the current time, and updates factor matrices (i. e., outputs of CP decomposition) instantly as new data arrives.
Learning to Pool in Graph Neural Networks for Extrapolation
However, according to a recent study, a careful choice of pooling functions, which are used for the aggregation and readout operations in GNNs, is crucial for enabling GNNs to extrapolate.
Efficient Neural Network Approximation of Robust PCA for Automated Analysis of Calcium Imaging Data
Calcium imaging is an essential tool to study the activity of neuronal populations.
Effective Training Strategies for Deep-learning-based Precipitation Nowcasting and Estimation
It is highlighted that our pre-training scheme and new loss function improve the critical success index (CSI) of nowcasting of heavy rainfall (at least 10 mm/hr) by up to 95. 7% and 43. 6%, respectively, at a 5-hr lead time.
Meta-Learning for Online Update of Recommender Systems
It is featured with an adaptive learning rate for each parameter-interaction pair for inducing a recommender to quickly learn users' up-to-date interest.
AHP: Learning to Negative Sample for Hyperedge Prediction
Since it is prohibitive to use all of them as negative examples for model training, it is inevitable to sample a very small portion of them, and to this end, heuristic sampling schemes have been employed.
I'm Me, We're Us, and I'm Us: Tri-directional Contrastive Learning on Hypergraphs
Although machine learning on hypergraphs has attracted considerable attention, most of the works have focused on (semi-)supervised learning, which may cause heavy labeling costs and poor generalization.
Set2Box: Similarity Preserving Representation Learning of Sets
Through extensive experiments on 8 real-world datasets, we show that, compared to baseline approaches, Set2Box+ is (a) Accurate: achieving up to 40. 8X smaller estimation error while requiring 60% fewer bits to encode sets, (b) Concise: yielding up to 96. 8X more concise representations with similar estimation error, and (c) Versatile: enabling the estimation of four set-similarity measures from a single representation of each set.
Deep-Learning-Based Precipitation Nowcasting with Ground Weather Station Data and Radar Data
Recently, many deep-learning techniques have been applied to various weather-related prediction tasks, including precipitation nowcasting (i. e., predicting precipitation levels and locations in the near future).
BeGin: Extensive Benchmark Scenarios and An Easy-to-use Framework for Graph Continual Learning
Compared to them, however, CL methods for graph data (graph CL) are relatively underexplored because of (a) the lack of standard experimental settings, especially regarding how to deal with the dependency between instances, (b) the lack of benchmark datasets and scenarios, and (c) high complexity in implementation and evaluation due to the dependency.
Region-Conditioned Orthogonal 3D U-Net for Weather4Cast Competition
The Weather4Cast competition (hosted by NeurIPS 2022) required competitors to predict super-resolution rain movies in various regions of Europe when low-resolution satellite contexts covering wider regions are given.
NeuKron: Constant-Size Lossy Compression of Sparse Reorderable Matrices and Tensors
The updates take time linear in the number of non-zeros in the input matrix, and the approximation of each entry can be retrieved in logarithmic time.
Towards Deep Attention in Graph Neural Networks: Problems and Remedies
AERO-GNN provably mitigates the proposed problems of deep graph attention, which is further empirically demonstrated with (a) its adaptive and less smooth attention functions and (b) higher performance at deep layers (up to 64).
Classification of Edge-dependent Labels of Nodes in Hypergraphs
Interestingly, many real-world systems modeled as hypergraphs contain edge-dependent node labels, i. e., node labels that vary depending on hyperedges.
Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs
Specifically, before the training procedure of a victim model, which is a TGNN for link prediction, we inject edge perturbations to the data that are unnoticeable in terms of the four constraints we propose, and yet effective enough to cause malfunction of the victim model.
TensorCodec: Compact Lossy Compression of Tensors without Strong Data Assumptions
While many tensor compression algorithms are available, many of them rely on strong data assumptions regarding its order, sparsity, rank, and smoothness.
Robust Graph Clustering via Meta Weighting for Noisy Graphs
We add a learnable weight to each node pair, and MetaGC adaptively adjusts the weights of node pairs using meta-weighting so that the weights of meaningful node pairs increase and the weights of less-meaningful ones (e. g., noise edges) decrease.
VITA: 'Carefully Chosen and Weighted Less' Is Better in Medication Recommendation
While there exist a number of recommender systems designed for this problem, we point out that they are challenged in accurately capturing the relation (spec., the degree of relevance) between the current and each of the past visits for the patient when obtaining her current health status, which is the basis for recommending medications.
Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective
Second, how does A-X dependence affect GNNs?
SLADE: Detecting Dynamic Anomalies in Edge Streams without Labels via Self-Supervised Learning
In this paper, we propose SLADE (Self-supervised Learning for Anomaly Detection in Edge Streams) for rapid detection of dynamic anomalies in edge streams, without relying on labels.
Self-Guided Robust Graph Structure Refinement
However, we have discovered that existing GSR methods are limited by narrowassumptions, such as assuming clean node features, moderate structural attacks, and the availability of external clean graphs, resulting in the restricted applicability in real-world scenarios.
FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer
The success of a specific neural network architecture is closely tied to the dataset and task it tackles; there is no one-size-fits-all solution.
HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs
Based on the generative SSL task, we propose a hypergraph SSL method, HypeBoy.
A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide
Higher-order interactions (HOIs) are ubiquitous in real-world complex systems and applications, and thus investigation of deep learning for HOIs has become a valuable agenda for the data mining and machine learning communities.
