Search Results for author:
Found 37 papers, 22 papers with code
Graph Neural Prompting with Large Language Models
While existing work has explored utilizing knowledge graphs to enhance language modeling via joint training and customized model architectures, applying this to LLMs is problematic owing to their large number of parameters and high computational cost.
Pure Message Passing Can Estimate Common Neighbor for Link Prediction
This discrepancy stems from a fundamental limitation: while MPNNs excel in node-level representation, they stumble with encoding the joint structural features essential to link prediction, like CN.
Information Fusion via Symbolic Regression: A Tutorial in the Context of Human Health
This tutorial paper provides a general overview of symbolic regression (SR) with specific focus on standards of interpretability.
What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks
In this paper, rather than pursuing state-of-the-art performance, we aim to evaluate capabilities of LLMs in a wide range of tasks across the chemistry domain.
Towards Understanding How Data Augmentation Works with Imbalanced Data
Data augmentation forms the cornerstone of many modern machine learning training pipelines; yet, the mechanisms by which it works are not clearly understood.
Class-Imbalanced Learning on Graphs: A Survey
Concerning the latter, we critically analyze recent work in CILG and discuss urgent lines of inquiry within the topic.
Conditional expectation with regularization for missing data imputation
Missing data frequently occurs in datasets across various domains, such as medicine, sports, and finance.
Knowledge Distillation on Graphs: A Survey
Therefore, to improve the applicability of GNNs and fully encode the complicated topological information, knowledge distillation on graphs (KDG) has been introduced to build a smaller yet effective model and exploit more knowledge from data, leading to model compression and performance improvement.
Interpretable ML for Imbalanced Data
We propose a set of techniques that can be used by both deep learning model users to identify, visualize and understand class prototypes, sub-concepts and outlier instances; and by imbalanced learning algorithm developers to detect features and class exemplars that are key to model performance.
FakeEdge: Alleviate Dataset Shift in Link Prediction
In this paper, we first identify the dataset shift problem in the link prediction task and provide theoretical analyses on how existing link prediction methods are vulnerable to it.
Linkless Link Prediction via Relational Distillation
In this work, to combine the advantages of GNNs and MLPs, we start with exploring direct knowledge distillation (KD) methods for link prediction, i. e., predicted logit-based matching and node representation-based matching.
NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs
Existing methods attempt to address this scalability issue by training multi-layer perceptrons (MLPs) exclusively on node content features using labels derived from trained GNNs.
Heterogeneous Graph Masked Autoencoders
In light of this, we study the problem of generative SSL on heterogeneous graphs and propose HGMAE, a novel heterogeneous graph masked autoencoder model to address these challenges.
Graph-based Molecular Representation Learning
Recently, MRL has achieved considerable progress, especially in methods based on deep molecular graph learning.
Deep Ensembles for Graphs with Higher-order Dependencies
Graph neural networks (GNNs) continue to achieve state-of-the-art performance on many graph learning tasks, but rely on the assumption that a given graph is a sufficient approximation of the true neighborhood structure.
Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural Networks
Learning effective recipe representations is essential in food studies.
RecipeRec: A Heterogeneous Graph Learning Model for Recipe Recommendation
We then propose RecipeRec, a novel heterogeneous graph learning model for recipe recommendation.
Few-Shot Learning on Graphs
In light of this, few-shot learning on graphs (FSLG), which combines the strengths of graph representation learning and few-shot learning together, has been proposed to tackle the performance degradation in face of limited annotated data challenge.
Predicting Terrorist Attacks in the United States using Localized News Data
From a machine learning perspective, we found that the Random Forest model outperformed several deep models on our multimodal, noisy, and imbalanced data set, thus demonstrating the efficacy of our novel feature representation method in such a context.
Graph Barlow Twins: A self-supervised representation learning framework for graphs
The self-supervised learning (SSL) paradigm is an essential exploration area, which tries to eliminate the need for expensive data labeling.
DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data
An important advantage of DeepSMOTE over GAN-based oversampling is that DeepSMOTE does not require a discriminator, and it generates high-quality artificial images that are both information-rich and suitable for visual inspection.
Few-Shot Graph Learning for Molecular Property Prediction
The recent success of graph neural networks has significantly boosted molecular property prediction, advancing activities such as drug discovery.
Ranked #1 on
Molecular Property Prediction (1-shot))
on Tox21
AttrE2vec: Unsupervised Attributed Edge Representation Learning
Representation learning has overcome the often arduous and manual featurization of networks through (unsupervised) feature learning as it results in embeddings that can apply to a variety of downstream learning tasks.
Learning Attribute-Structure Co-Evolutions in Dynamic Graphs
In this work, we present a novel framework called CoEvoGNN for modeling dynamic attributed graph sequence.
Canonicalizing Open Knowledge Bases with Multi-Layered Meta-Graph Neural Network
Noun phrases and relational phrases in Open Knowledge Bases are often not canonical, leading to redundant and ambiguous facts.
Calendar Graph Neural Networks for Modeling Time Structures in Spatiotemporal User Behaviors
The user embeddings preserve spatial patterns and temporal patterns of a variety of periodicity (e. g., hourly, weekly, and weekday patterns).
Jointly Predicting Job Performance, Personality, Cognitive Ability, Affect, and Well-Being
In this paper, we create a benchmark for predictive analysis of individuals from a perspective that integrates: physical and physiological behavior, psychological states and traits, and job performance.
Few-Shot Knowledge Graph Completion
Knowledge graphs (KGs) serve as useful resources for various natural language processing applications.
Graph Few-shot Learning via Knowledge Transfer
Towards the challenging problem of semi-supervised node classification, there have been extensive studies.
HONEM: Learning Embedding for Higher Order Networks
Representation learning on networks offers a powerful alternative to the oft painstaking process of manual feature engineering, and as a result, has enjoyed considerable success in recent years.
Constructing Information-Lossless Biological Knowledge Graphs from Conditional Statements
Conditions are essential in the statements of biological literature.
FILDNE: A Framework for Incremental Learning of Dynamic Networks Embeddings
Experimental results on several downstream tasks, over seven real-world data sets, show that FILDNE is able to reduce memory and computational time costs while providing competitive quality measure gains with respect to the contemporary methods for representation learning on dynamic graphs.
A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data
Subsequently, given the signature matrices, a convolutional encoder is employed to encode the inter-sensor (time series) correlations and an attention based Convolutional Long-Short Term Memory (ConvLSTM) network is developed to capture the temporal patterns.
Detecting Anomalies in Sequential Data with Higher-order Networks
A major branch of anomaly detection methods relies on dynamic networks: raw sequence data is first converted to a series of networks, then critical change points are identified in the evolving network structure.
Social and Information Networks Physics and Society
Beyond Volume: The Impact of Complex Healthcare Data on the Machine Learning Pipeline
From medical charts to national census, healthcare has traditionally operated under a paper-based paradigm.
Will This Paper Increase Your h-index? Scientific Impact Prediction
The effectiveness of such predictions, however, is fundamentally limited by the power-law distribution of citations, whereby publications with few citations are extremely common and publications with many citations are relatively rare.
Social and Information Networks Digital Libraries Physics and Society H.2.8; H.3.7
Predicting Online Video Engagement Using Clickstreams
In the nascent days of e-content delivery, having a superior product was enough to give companies an edge against the competition.
