Sami Abu-El-Haija — accepted AI-conference papers

2023

Learning Large Graph Property Prediction via Graph Segment Training

Kaidi Cao, Phitchaya Mangpo Phothilimthana, Sami Abu-El-Haija, Dustin Zelle, Yanqi Zhou, Charith Mendis +2

NeurIPS 2023poster

Learning to predict properties of large graphs is challenging because each prediction requires the knowledge of an entire graph, while the amount of memory available during training is bounded. Here we propose Graph Segment Training (GST), a general framework that utilizes a divide-and-conquer appro…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗

2023

SubMix: Learning to Mix Graph Sampling Heuristics

Sami Abu-El-Haija, Joshua V. Dillon, Bahare Fatemi, Kyriakos Axiotis, Neslihan Bulut, Johannes Gasteiger +2

UAI 2023poster

Sampling subgraphs for training Graph Neural Networks (GNNs) is receiving much attention from the GNN community. While a variety of methods have been proposed, each method samples the graph according to its own heuristic. However, there has been little work in mixing these heuristics in an end-to-en…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2023

TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs

Phitchaya Mangpo Phothilimthana, Sami Abu-El-Haija, Kaidi Cao, Bahare Fatemi, Michael Burrows, Charith Mendis +1

NeurIPS 2023poster

Precise hardware performance models play a crucial role in code optimizations. They can assist compilers in making heuristic decisions or aid autotuners in identifying the optimal configuration for a given program. For example, the autotuner for XLA, a machine learning compiler, discovered 10–20\% s…

Cited by 16 Source ↗PDF ↗code ↗Scholar ↗

2021

Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learning

Elan Sopher Markowitz, Keshav Balasubramanian, Mehrnoosh Mirtaheri, Sami Abu-El-Haija, Bryan Perozzi, Greg Ver Steeg +1

ICLR 2021poster

Graph Representation Learning (GRL) methods have impacted fields from chemistry to social science. However, their algorithmic implementations are specialized to specific use-cases e.g. "message passing" methods are run differently from "node embedding" ones. Despite their apparent differences, all t…

Cited by 26 Source ↗PDF ↗code ↗Scholar ↗

2021

Implicit SVD for Graph Representation Learning

Sami Abu-El-Haija, Hesham Mostafa, Marcel Nassar, Valentino Crespi, Greg Ver Steeg, Aram Galstyan

NeurIPS 2021poster

Recent improvements in the performance of state-of-the-art (SOTA) methods for Graph Representational Learning (GRL) have come at the cost of significant computational resource requirements for training, e.g., for calculating gradients via backprop over many data epochs. Meanwhile, Singular Value Dec…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗

2021

Zero-shot Synthesis with Group-Supervised Learning

Yunhao Ge, Sami Abu-El-Haija, Gan Xin, Laurent Itti

ICLR 2021poster

Visual cognition of primates is superior to that of artificial neural networks in its ability to “envision” a visual object, even a newly-introduced one, in different attributes including pose, position, color, texture, etc. To aid neural networks to envision objects with different attributes, we…

Cited by 56 Source ↗PDF ↗Scholar ↗

2019

MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Nazanin Alipourfard, Kristina Lerman, Hrayr Harutyunyan +2

ICML 2019oral

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. To address this weakness, we propose a new model, MixHop, that can learn these relationships, includi…

Cited by 1185 Source ↗PDF ↗code ↗Scholar ↗

2019

N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification

Sami Abu-El-Haija, Amol Kapoor, Bryan Perozzi, Joonseok Lee

UAI 2019poster

Graph Convolutional Networks (GCNs) have shown significant improvements in semi-supervised learning on graph-structured data. Concurrently, unsupervised learning of graph embeddings has benefited from the information contained in random walks. In this paper, we propose a model: Network of GCNs (N-GC…

Cited by 356 Source ↗PDF ↗code ↗Scholar ↗

2018

Watch Your Step: Learning Node Embeddings via Graph Attention

Sami Abu-El-Haija, Bryan Perozzi, Rami Al-Rfou, Alexander A Alemi

NeurIPS 2018poster

Graph embedding methods represent nodes in a continuous vector space, preserving different types of relational information from the graph. There are many hyper-parameters to these methods (e.g. the length of a random walk) which have to be manually tuned for every graph. In this paper, we replace pr…

Cited by 298 Source ↗PDF ↗Scholar ↗

2016

Detecting Events and Key Actors in Multi-Person Videos

Vignesh Ramanathan, Jonathan Huang, Sami Abu-El-Haija, Alexander Gorban, Kevin Murphy, Li Fei-Fei

CVPR 2016oral

Multi-person event recognition is a challenging task, often with many people active in the scene but only a small subset contributing to an actual event. In this paper, we propose a model which learns to detect events in such videos while automatically "attending" to the people responsible for the e…

Cited by 284 PDF ↗Scholar ↗