Search Results for author:
Found 54 papers, 31 papers with code
Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights
First, the absence of a comprehensive benchmark with unified problem settings hinders a clear understanding of the comparative effectiveness and practical value of different text-space GFMs.
Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning
Large language models (LLMs) have showcased remarkable reasoning capabilities, yet they remain susceptible to errors, particularly in temporal reasoning tasks involving complex temporal logic.
Understanding Transformer Reasoning Capabilities via Graph Algorithms
Our novel representational hierarchy separates 9 algorithmic reasoning problems into classes solvable by transformers in different realistic parameter scaling regimes.
Don't Forget to Connect! Improving RAG with Graph-based Reranking
Retrieval Augmented Generation (RAG) has greatly improved the performance of Large Language Model (LLM) responses by grounding generation with context from existing documents.
Let Your Graph Do the Talking: Encoding Structured Data for LLMs
How can we best encode structured data into sequential form for use in large language models (LLMs)?
The Graph Lottery Ticket Hypothesis: Finding Sparse, Informative Graph Structure
Subsequently, we define the notion of a "winning ticket" for graph structure - an extremely sparse subset of edges that can deliver a robust approximation of the entire graph's performance.
Talk like a Graph: Encoding Graphs for Large Language Models
Graphs are a powerful tool for representing and analyzing complex relationships in real-world applications such as social networks, recommender systems, and computational finance.
TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs
TpuGraphs provides 25x more graphs than the largest graph property prediction dataset (with comparable graph sizes), and 770x larger graphs on average compared to existing performance prediction datasets on machine learning programs.
Ranked #2 on
Runtime ranking
on TpuGraphs Layout mean
UGSL: A Unified Framework for Benchmarking Graph Structure Learning
We implement a wide range of existing models in our framework and conduct extensive analyses of the effectiveness of different components in the framework.
HUGE: Huge Unsupervised Graph Embeddings with TPUs
A high-performance graph embedding architecture leveraging Tensor Processing Units (TPUs) with configurable amounts of high-bandwidth memory is presented that simplifies the graph embedding problem and can scale to graphs with billions of nodes and trillions of edges.
Examining the Effects of Degree Distribution and Homophily in Graph Learning Models
In this work we examine how two additional synthetic graph generators can improve GraphWorld's evaluation; LFR, a well-established model in the graph clustering literature and CABAM, a recent adaptation of the Barabasi-Albert model tailored for GNN benchmarking.
Explaining and Adapting Graph Conditional Shift
Graph Neural Networks (GNNs) have shown remarkable performance on graph-structured data.
Unsupervised Embedding Quality Evaluation
Unsupervised learning has recently significantly gained in popularity, especially with deep learning-based approaches.
Learning Large Graph Property Prediction via Graph Segment Training
Here we propose Graph Segment Training (GST), a general framework that utilizes a divide-and-conquer approach to allow learning large graph property prediction with a constant memory footprint.
On Classification Thresholds for Graph Attention with Edge Features
In CSBM the nodes and edge features are obtained from a mixture of Gaussians and the edges from a stochastic block model.
Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank
Personalized PageRank (PPR) is a fundamental tool in unsupervised learning of graph representations such as node ranking, labeling, and graph embedding.
Graph Generative Model for Benchmarking Graph Neural Networks
As the field of Graph Neural Networks (GNN) continues to grow, it experiences a corresponding increase in the need for large, real-world datasets to train and test new GNN models on challenging, realistic problems.
TF-GNN: Graph Neural Networks in TensorFlow
TensorFlow-GNN (TF-GNN) is a scalable library for Graph Neural Networks in TensorFlow.
Tackling Provably Hard Representative Selection via Graph Neural Networks
Representative Selection (RS) is the problem of finding a small subset of exemplars from a dataset that is representative of the dataset.
Synthetic Graph Generation to Benchmark Graph Learning
This shockingly small sample size (~10) allows for only limited scientific insight into the problem.
Zero-shot Transfer Learning within a Heterogeneous Graph via Knowledge Transfer Networks
We propose a zero-shot transfer learning module for HGNNs called a Knowledge Transfer Network (KTN) that transfers knowledge from label-abundant node types to zero-labeled node types through rich relational information given in the HG.
GraphWorld: Fake Graphs Bring Real Insights for GNNs
Using GraphWorld, a user has fine-grained control over graph generator parameters, and can benchmark arbitrary GNN models with built-in hyperparameter tuning.
Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data
In this work we present a method, Shift-Robust GNN (SR-GNN), designed to account for distributional differences between biased training data and the graph's true inference distribution.
Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learning
We propose Graph Traversal via Tensor Functionals(GTTF), a unifying meta-algorithm framework for easing the implementation of diverse graph algorithms and enabling transparent and efficient scaling to large graphs.
Pathfinder Discovery Networks for Neural Message Passing
Additional results from a challenging suite of node classification experiments show how PDNs can learn a wider class of functions than existing baselines.
InstantEmbedding: Efficient Local Node Representations
In this paper, we introduce InstantEmbedding, an efficient method for generating single-node representations using local PageRank computations.
Grale: Designing Networks for Graph Learning
Interestingly, there are often many types of similarity available to choose as the edges between nodes, and the choice of edges can drastically affect the performance of downstream semi-supervised learning systems.
Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networks
In this work, we examine a novel forecasting approach for COVID-19 case prediction that uses Graph Neural Networks and mobility data.
Scaling Graph Neural Networks with Approximate PageRank
Graph neural networks (GNNs) have emerged as a powerful approach for solving many network mining tasks.
Graph Clustering with Graph Neural Networks
Graph Neural Networks (GNNs) have achieved state-of-the-art results on many graph analysis tasks such as node classification and link prediction.
Machine Learning on Graphs: A Model and Comprehensive Taxonomy
The second, graph regularized neural networks, leverages graphs to augment neural network losses with a regularization objective for semi-supervised learning.
Just SLaQ When You Approximate: Accurate Spectral Distances for Web-Scale Graphs
Graph comparison is a fundamental operation in data mining and information retrieval.
MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit
In this paper, we show that when metadata is correlated with the formation of node neighborhoods, unsupervised node embedding dimensions learn this metadata.
Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts
Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph.
MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
Existing popular methods for semi-supervised learning with Graph Neural Networks (such as the Graph Convolutional Network) provably cannot learn a general class of neighborhood mixing relationships.
DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
Second, for each pair of graphs, we train a cross-graph attention network which uses the node representations of an anchor graph to reconstruct another graph.
Ranked #3 on
Graph Classification
on D&D
Splitter: Learning Node Representations that Capture Multiple Social Contexts
Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph.
Enhanced Network Embeddings via Exploiting Edge Labels
Network embedding methods aim at learning low-dimensional latent representation of nodes in a network.
Social and Information Networks Physics and Society
A Tutorial on Network Embeddings
We further demonstrate the applications of network embeddings, and conclude the survey with future work in this area.
Social and Information Networks
N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification
Graph Convolutional Networks (GCNs) have shown significant improvements in semi-supervised learning on graph-structured data.
Ranked #41 on
Node Classification
on Pubmed
Network of Graph Convolutional Networks Trained on Random Walks
Graph Convolutional Networks (GCNs) are a recently proposed architecture which has had success in semi-supervised learning on graph-structured data.
Watch Your Step: Learning Node Embeddings via Graph Attention
Graph embedding methods represent nodes in a continuous vector space, preserving information from the graph (e. g. by sampling random walks).
Ranked #67 on
Node Classification
on Citeseer
HARP: Hierarchical Representation Learning for Networks
We present HARP, a novel method for learning low dimensional embeddings of a graph's nodes which preserves higher-order structural features.
Social and Information Networks
Learning Edge Representations via Low-Rank Asymmetric Projections
Individually, both of these contributions improve the learned representations, especially when there are memory constraints on the total size of the embeddings.
On the Convergent Properties of Word Embedding Methods
Do word embeddings converge to learn similar things over different initializations?
Don't Walk, Skip! Online Learning of Multi-scale Network Embeddings
We present Walklets, a novel approach for learning multiscale representations of vertices in a network.
Social and Information Networks Physics and Society
Freshman or Fresher? Quantifying the Geographic Variation of Internet Language
Our analysis of British and American English over a period of 100 years reveals that semantic variation between these dialects is shrinking.
Statistically Significant Detection of Linguistic Change
We propose a new computational approach for tracking and detecting statistically significant linguistic shifts in the meaning and usage of words.
POLYGLOT-NER: Massive Multilingual Named Entity Recognition
We describe a system that builds Named Entity Recognition (NER) annotators for 40 major languages using Wikipedia and Freebase.
Exploring the power of GPU's for training Polyglot language models
We evaluate the performance of training the model on the GPU and present optimizations that boost the performance on the GPU. One of the key optimizations, we propose increases the performance of a function involved in calculating and updating the gradient by approximately 50 times on the GPU for sufficiently large batch sizes.
DeepWalk: Online Learning of Social Representations
We present DeepWalk, a novel approach for learning latent representations of vertices in a network.
Ranked #1 on
Link Property Prediction
on ogbl-ppa
Inducing Language Networks from Continuous Space Word Representations
Recent advancements in unsupervised feature learning have developed powerful latent representations of words.
Polyglot: Distributed Word Representations for Multilingual NLP
We quantitatively demonstrate the utility of our word embeddings by using them as the sole features for training a part of speech tagger for a subset of these languages.
The Expressive Power of Word Embeddings
We seek to better understand the difference in quality of the several publicly released embeddings.
