free css templates

Keynote 1

Deep Graph Library: Overview, Updates, and Future Developments

George Karypis
(AWS Deep Learning Science  & University of Minnesota)

Learning from graph and relational data plays a major role in many applications including social network analysis, marketing, e-commerce, information retrieval, knowledge modeling, medical and biological sciences, engineering, and others. In the last few years, Graph Neural Networks (GNNs) have emerged as a promising new supervised learning framework capable of bringing the power of deep representation learning to graph and relational data. This ever-growing body of research has shown that GNNs achieve state-of-the-art performance for problems such as link prediction, fraud detection, target-ligand binding activity prediction, knowledge-graph completion, and product recommendations.

Deep Graph Library (DGL) is an open source development framework for writing and training GNN-based models. It is designed to simplify the development of such models by using graph-based abstractions while at the same time achieving high computational efficiency and scalability by relying on optimized sparse matrix operations and existing highly optimized standard deep learning frameworks (e.g., MXNet, PyTorch, and TensorFlow). This talk provides an overview of DGL, describes some recent developments related to high-performance multi-GPU, multi-core, and distributed training, and describes our future development roadmap.


George Karypis is a Distinguished McKnight University Professor and an ADC Chair of Digital Technology at the Department of Computer Science & Engineering at the University of Minnesota, Twin Cities. His research interests span the areas of data mining, high performance computing, information retrieval, collaborative filtering, bioinformatics, cheminformatics, and scientific computing. His research has resulted in the development of software libraries for serial and parallel graph partitioning (METIS and ParMETIS), hypergraph partitioning (hMETIS), for parallel Cholesky factorization (PSPASES), for collaborative filtering-based recommendation algorithms (SUGGEST), clustering high dimensional datasets (CLUTO), finding frequent patterns in diverse datasets (PAFI), and for protein secondary structure prediction (YASSPP). He has coauthored over 280 papers on these topics and two books (“Introduction to Protein Structure Prediction: Methods and Algorithms” (Wiley, 2010) and “Introduction to Parallel Computing” (Publ. Addison Wesley, 2003, 2nd edition)). In addition, he is serving on the program committees of many conferences and workshops on these topics, and on the editorial boards of the IEEE Transactions on Knowledge and Data Engineering, ACM Transactions on Knowledge Discovery from Data, Data Mining and Knowledge Discovery, Social Network Analysis and Data Mining Journal, International Journal of Data Mining and Bioinformatics, the journal on Current Proteomics, Advances in Bioinformatics, and Biomedicine and Biotechnology. He is a Fellow of the IEEE.

Keynote 2

The GraphIt Universal Graph Framework: Achieving High-Performance across Algorithms, Graph Types, and Architectures

Saman Amarasinghe (Massachusetts Institute of Technology)

In recent years, large graphs with billions of vertices and trillions of edges have emerged in many domains, such as social network analytics, machine learning, physical simulations, and biology. However, optimizing the performance of graph applications is notoriously difficult due to irregular memory access patterns and load imbalance across cores. The performance of graph programs depends highly on the algorithm, the size, and structure of the input graphs, as well as the features of the underlying hardware. No single set of optimizations or single hardware platform works well across all applications.

In this talk, I will present the GraphIt Universal Graph Framework, a domain-specific language (DSL) that achieves consistent high-performance across different algorithms, graphs, and architectures, while offering an easy-to-use high-level programming model. GraphIt language decouples the program specification (algorithm language) from performance optimizations (scheduling language), and the GraphIt compiler separates hardware-independent transformations from multiple architecture-specific backends (GraphVMs). I will describe how GraphIt achieves up to 4.8x speedup over state-of-the-art graph frameworks on CPUs and GPUs, while reducing the lines of code by up to an order of magnitude.


Saman P. Amarasinghe is a Professor in the Department of Electrical Engineering and Computer Science at Massachusetts Institute of Technology and a member of its Computer Science and Artificial Intelligence Laboratory (CSAIL) where he leads the Commit compiler group. Under Saman's guidance, the Commit group developed the StreamIt, StreamJIT, PetaBricks, Halide, Simit, MILK, Cimple, TACO, GraphIt, Tiramisu, BioStream and Seq domain specific languages and compilers, DynamoRIO dynamic instrumentation system, Superword level parallelism for SIMD vectorization, Program Shepherding to protect programs against external attacks, the OpenTuner extendable autotuner, and the Kendo deterministic execution system. He was the co-leader of the Raw architecture project. Saman was the founder of Determina Corporation, and a co-founder of Lanka Internet Services Ltd., and Venti Technologies Corporation. Saman received his BS in Electrical Engineering and Computer Science from Cornell University in 1988, and his MSEE and Ph.D. from Stanford University in 1990 and 1997, respectively. He is an ACM Fellow.