Force2Vec: Parallel Force-Directed Graph Embedding

Rahman, Md. Khaledur; Sujon, Majedul Haque; Azad, Ariful

doi:10.1109/icdm50108.2020.00053

Cited by 17 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If we aim to implement SDDMM and SpMM separately, we could use either 1D (i.e., vertex partitioning) or 2D (edge partitioning) partitioning of the adjacency matrix A. However, when we fuse SDDMM and SpMM in FusedMM, 2D partitioning of A may be very inefficient or even outright [4] and VERSE [3] with sigmoid) Fig. 1 {A 1 , ...,…”

Section: The Parallel Fusedmm Algorithmmentioning

confidence: 99%

“…If we recognize a pattern from predefined VOP, ROP, SOP, MOP, and AOP operations, we can optimize the whole kernel by feeding the output of one operation directly to the next operation without storing the results. For example, the second row in Table III uses the (MUL, RSUM, SIGMOID, MUL, ASUM) sequence of operations, which is a common pattern used by various node embedding algorithms such as VERSE [3] and Force2Vec [4]. Hence, we develop optimized FusedMM kernels for patterns denoted by the first three rows in Table III.…”

Section: Optimizations and Code Generationmentioning

confidence: 99%

“…For example, the original GCN implementation from Kipf and Welling [5] used SpMM to capture the graph convolution operation. SpMM-like operations were also used in high-performance graph layout [2] and embedding [4] algorithms.…”

Section: End-to-end Trainingmentioning

confidence: 99%

“…Here, N (u) denotes inneighbors of u, ψ and φ are application-defined functions and is an application-defined aggregator. By changing the functions ψ, φ, and , we can easily derive forcedirected graph layout [1,2], graph embedding [3,4], graph convolutional network (GCN) [5], and graph neural networks (GNNs) algorithms [6] as shown in Fig. 1.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

FusedMM: A Unified SDDMM-SpMM Kernel for Graph Embedding and Graph Neural Networks

Rahman

Sujon

Azad

2021

2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)

Self Cite

View full text Add to dashboard Cite

We develop a fused matrix multiplication kernel that unifies sampled dense-dense matrix multiplication and sparsedense matrix multiplication under a single operation called FusedMM. By using user-defined functions, FusedMM can capture almost all computational patterns needed by popular graph embedding and GNN approaches.FusedMM is an order of magnitude faster than its equivalent kernels in Deep Graph Library. The superior performance of FusedMM comes from the low-level vectorized kernels, a suitable load balancing scheme and an efficient utilization of the memory bandwidth. FusedMM can tune its performance using a code generator and perform equally well on Intel, AMD and ARM processors. FusedMM speeds up an end-to-end graph embedding algorithm by up to 28× on different processors.

show abstract

Section: The Parallel Fusedmm Algorithmmentioning

confidence: 99%

Section: Optimizations and Code Generationmentioning

confidence: 99%

Section: End-to-end Trainingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

FusedMM: A Unified SDDMM-SpMM Kernel for Graph Embedding and Graph Neural Networks

Rahman

Sujon

Azad

2021

2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Several unsupervised methods have been proposed in the literature to solve this problem sub-optimally [5,11]. Graph layout generation methods can also be used to generate embedding [12,13]. Some of them generate good quality embedding but have high runtime and memory costs while some of them consume less runtime and memory costs but generate moderate-quality embedding.…”

mentioning

confidence: 99%

Training Sensitivity in Graph Isomorphism Network

Rahman

2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

Self Cite

View full text Add to dashboard Cite

Graph neural network (GNN) is a popular tool to learn the lowerdimensional representation of a graph. It facilitates the applicability of machine learning tasks on graphs by incorporating domainspecific features. There are various options for underlying procedures (such as optimization functions, activation functions, etc.) that can be considered in the implementation of GNN. However, most of the existing tools are confined to one approach without any analysis. Thus, this emerging field lacks a robust implementation ignoring the highly irregular structure of the real-world graphs. In this paper, we attempt to fill this gap by studying various alternative functions for a respective module using a diverse set of benchmark datasets. Our empirical results suggest that the generally used underlying techniques do not always perform well to capture the overall structure from a set of graphs. CCS CONCEPTS • Computing methodologies → Neural networks.

show abstract

Visualizing Evolving Trees

Gray

Ahmed

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Large tree structures are ubiquitous and real-world relational datasets often have information associated with nodes (e.g., labels or other attributes) and edges (e.g., weights or distances) that need to be communicated to the viewers. Yet, scalable, easy to read tree layouts are difficult to achieve. We consider tree layouts to be readable if they meet some basic requirements: node labels should not overlap, edges should not cross, edge lengths should be preserved, and the output should be compact. There are many algorithms for drawing trees, although very few take node labels or edge lengths into account, and none optimizes all requirements above. With this in mind, we propose a new scalable method for readable tree layouts. The algorithm guarantees that the layout has no edge crossings and no label overlaps, and optimizes one of the remaining aspects: desired edge lengths and compactness. We evaluate the performance of the new algorithm by comparison with related earlier approaches using several real-world datasets, ranging from a few thousand nodes to hundreds of thousands of nodes. Tree layout algorithms can be used to visualize large general graphs, by extracting a hierarchy of progressively larger trees. We illustrate this functionality by presenting several map-like visualizations generated by the new tree layout algorithm.

show abstract

Force2Vec: Parallel Force-Directed Graph Embedding

Cited by 17 publications

References 21 publications

FusedMM: A Unified SDDMM-SpMM Kernel for Graph Embedding and Graph Neural Networks

FusedMM: A Unified SDDMM-SpMM Kernel for Graph Embedding and Graph Neural Networks

Training Sensitivity in Graph Isomorphism Network

Visualizing Evolving Trees

Contact Info

Product

Resources

About