Tim Kaler
YOU?
Author Swipe
View article: Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve
Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve Open
Recent studies show that LLMs possess different skills and specialize in different tasks. In fact, we observe that their varied performance occur in several levels of granularity. For example, in the code optimization task, code LLMs excel…
View article: The Shape of Money Laundering: Subgraph Representation Learning on the Blockchain with the Elliptic2 Dataset
The Shape of Money Laundering: Subgraph Representation Learning on the Blockchain with the Elliptic2 Dataset Open
Subgraph representation learning is a technique for analyzing local structures (or shapes) within complex networks. Enabled by recent developments in scalable Graph Neural Networks (GNNs), this approach encodes relational information at a …
View article: Communication-Efficient Graph Neural Networks with Probabilistic Neighborhood Expansion Analysis and Caching
Communication-Efficient Graph Neural Networks with Probabilistic Neighborhood Expansion Analysis and Caching Open
Training and inference with graph neural networks (GNNs) on massive graphs has been actively studied since the inception of GNNs, owing to the widespread use and success of GNNs in applications such as recommendation systems and financial …
View article: Executing Dynamic Data-Graph Computations Deterministically Using Chromatic Scheduling
Executing Dynamic Data-Graph Computations Deterministically Using Chromatic Scheduling Open
A data-graph computation -popularized by such programming systems as Galois, Pregel, GraphLab, PowerGraph, and GraphChi -is an algorithm that performs local updates on the vertices of a graph.During each round of a data-graph computation, …
View article: Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining
Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining Open
Abstract Improving the training and inference performance of graph neural networks (GNNs) is faced with a challenge uncommon in general neural networks: creating mini-batches requires a lot of computation and data movement due to the expon…
View article: Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining
Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining Open
Improving the training and inference performance of graph neural networks (GNNs) is faced with a challenge uncommon in general neural networks: creating mini-batches requires a lot of computation and data movement due to the exponential gr…
View article: EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs Open
Graph representation learning resurges as a trending research subject owing to the widespread use of deep learning for Euclidean data, which inspire various creative designs of neural networks in the non-Euclidean domain, particularly grap…
View article: Cilkmem: Algorithms for Analyzing the Memory High-Water Mark of Fork-Join Parallel Programs
Cilkmem: Algorithms for Analyzing the Memory High-Water Mark of Fork-Join Parallel Programs Open
Software engineers designing recursive fork-join programs destined to run on massively parallel computing systems must be cognizant of how their program's memory requirements scale in a many-processor execution. Although tools exist for me…
View article: Cilkmem: Algorithms for Analyzing the Memory High-Water Mark of Fork-Join Parallel Programs
Cilkmem: Algorithms for Analyzing the Memory High-Water Mark of Fork-Join Parallel Programs Open
Software engineers designing recursive fork-join programs destined to run on massively parallel computing systems must be cognizant of how their program's memory requirements scale in a many-processor execution. Although tools exist for me…
View article: Scalable Graph Learning for Anti-Money Laundering: A First Look
Scalable Graph Learning for Anti-Money Laundering: A First Look Open
Organized crime inflicts human suffering on a genocidal scale: the Mexican drug cartels have murdered 150,000 people since 2006, upwards of 700,000 people per year are "exported" in a human trafficking industry enslaving an estimated 40 mi…
View article: Optimal Reissue Policies for Reducing Tail Latency
Optimal Reissue Policies for Reducing Tail Latency Open
Interactive services send redundant requests to multiple different replicas to meet stringent tail latency requirements. These addi- tional (reissue) requests mitigate the impact of non-deterministic delays within the system and thus incre…
View article: A Multicore Path to Connectomics-on-Demand
A Multicore Path to Connectomics-on-Demand Open
The current design trend in large scale machine learning is to use distributed clusters of CPUs and GPUs with MapReduce-style programming. Some have been led to believe that this type of horizontal scaling can reduce or even eliminate the …