Search for: All records

Large Language Models (LLMs) heavily rely on high-quality training data, making data valuation crucial for optimizing model performance, especially when working within a limited budget. In this work, we aim to offer a third-party data valuation approach that benefits both data providers and model developers. We introduce a linearized future influence kernel (LinFiK), which assesses the value of individual data samples in improving LLM performance during training. We further propose ALinFiK, a learning strategy to approximate LinFiK, enabling scalable data valuation. Our comprehensive evaluations demonstrate that this approach surpasses existing baselines in effectiveness and efficiency, demonstrating significant scalability advantages as LLM parameters increase. 

Error-bounded lossy compression has been effective in significantly reducing the data storage/transfer burden while preserving the reconstructed data fidelity very well. Many error-bounded lossy compressors have been developed for a wide range of parallel and distributed use cases for years. They are designed with distinct compression models and principles, such that each of them features particular pros and cons. In this paper we provide a comprehensive survey of emerging error-bounded lossy compression techniques. The key contribution is fourfold. (1) We summarize a novel taxonomy of lossy compression into 6 classic models. (2) We provide a comprehensive survey of 10 commonly used compression components/modules. (3) We summarized pros and cons of 47 state-of-the-art lossy compressors and present how state-of-the-art compressors are designed based on different compression techniques. (4) We discuss how customized compressors are designed for specific scientific applications and use-cases. We believe this survey is useful to multiple communities including scientific applications, high-performance computing, lossy compression, and big data. 

Finding from a big graph those subgraphs that satisfy certain conditions (aka. subgraph search) is useful in many applications such as community detection and subgraph matching. These problems often generate a search-space tree with size exponential to the size of the input graph. GPUs with thousands of cores are a natural choice to speed up subgraph search, but existing GPU solutions either conduct BFS on the search-space tree which leads to memory overflow due to intermediate subgraph-size explosion, or they conduct DFS on the search-space tree which is memory-efficient but can be 2 orders of magnitude slower than a BFS solution. In this paper, we present G2-AIMD, a subgraph-centric framework for efficient subGraph Search on GPUs, which enjoys the efficiency of BFS on the search-space tree, while avoids intermediate subgraph-size explosion with novel system designs such as adaptive chunk-size adjustment and host-memory subgraph buffering, inspired by the additive-increase/multiplicative-decrease (AIMD) algorithm in TCP congestion control. G2-AIMD provides a convenient subgraph-centric programming interface to facilitate the implementation of subgraph search algorithms on top, so as to enjoy the above performance merits. G2-AIMD also supports multi-GPU execution where each GPU only needs to load a fraction of the input graph. To demonstrate the efficiency and scalability of G2-AIMD, two algorithms were implemented on top with additional optimization techniques, and they significantly outperform the existing GPU solutions.