Related papers: A-Graph: A Unified Graph Representation for At-Wil…
The scalability and efficiency of graph applications are significantly constrained by conventional systems and their supporting programming models. Technology trends like multicore, manycore, and heterogeneous system architectures are…
Current applications have produced graphs on the order of hundreds of thousands of nodes and millions of edges. To take advantage of such graphs, one must be able to find patterns, outliers and communities. These tasks are better performed…
Optimizing the performance of large-scale parallel codes is critical for efficient utilization of computing resources. Code developers often explore various execution parameters, such as hardware configurations, system software choices, and…
Given a node-attributed graph, how can we efficiently represent it with few numerical features that expressively reflect its topology and attribute information? We propose A-DOGE, for Attributed DOS-based Graph Embedding, based on density…
Graph embedding algorithms are used to efficiently represent (encode) a graph in a low-dimensional continuous vector space that preserves the most important properties of the graph. One aspect that is often overlooked is whether the graph…
The vast amounts of data used in social, business or traffic networks, biology and other natural sciences are often managed in graph-based data sets, consisting of a few thousand up to billions and trillions of vertices and edges,…
The topological (or graph) structures of real-world networks are known to be predictive of multiple dynamic properties of the networks. Conventionally, a graph structure is represented using an adjacency matrix or a set of hand-crafted…
GPU architectures have become popular for executing general-purpose programs. Their many-core architecture supports a large number of threads that run concurrently to hide the latency among dependent instructions. In modern GPU…
Benchmarking and co-design are essential for driving optimizations and innovation around ML models, ML software, and next-generation hardware. Full workload benchmarks, e.g. MLPerf, play an essential role in enabling fair comparison across…
We present ALX, an open-source library for distributed matrix factorization using Alternating Least Squares, written in JAX. Our design allows for efficient use of the TPU architecture and scales well to matrix factorization problems of…
Coarse-grained Reconfigurable Arrays (CGRAs) are domain-agnostic accelerators that enhance the energy efficiency of resource-constrained edge devices. The CGRA landscape is diverse, exhibiting trade-offs between performance, efficiency, and…
Large graphs can be found in a wide array of scientific fields ranging from sociology and biology to scientometrics and computer science. Their analysis is by no means a trivial task due to their sheer size and complex structure. Such…
Graph comparison is a fundamental operation in data mining and information retrieval. Due to the combinatorial nature of graphs, it is hard to balance the expressiveness of the similarity measure and its scalability. Spectral analysis…
Advancing research in the emerging field of deep graph learning requires new tools to support tensor computation over graphs. In this paper, we present the design principles and implementation of Deep Graph Library (DGL). DGL distills the…
We equip dynamic geometry software (DGS) with a user-friendly method that enables massively parallel calculations on the graphics processing unit (GPU). This interplay of DGS and GPU opens up various applications in education and…
Self-stabilizing algorithms are an important because of their robustness and guaranteed convergence. Starting from any arbitrary state, a self-stabilizing algorithm is guaranteed to converge to a legitimate state.Those algorithms are not…
Recent deep learning models have moved beyond low-dimensional regular grids such as image, video, and speech, to high-dimensional graph-structured data, such as social networks, brain connections, and knowledge graphs. This evolution has…
Graphical User Interface (GUI) agents adopt an end-to-end paradigm that maps a screenshot to an action sequence, thereby automating repetitive tasks in virtual environments. However, existing GUI agents are evaluated almost exclusively on…
Due to their high computational efficiency on a continuous space, gradient optimization methods have shown great potential in the neural architecture search (NAS) domain. The mapping of network representation from the discrete space to a…
Despite the success of automated machine learning (AutoML), which aims to find the best design, including the architecture of deep networks and hyper-parameters, conventional AutoML methods are computationally expensive and hardly provide…