More Like this

1. RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking

   Zou, Jiaru; Fu, Dongqi; Chen, Sirui; He, Xinrui; Li, Zihao; Zhu, Yada; Han, Jiawei; He, Jingrui (July 2026, Association for Computational Linguistics: Findings of the Association for Computational Linguistics, ACL-2026)

   Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating them with an external knowledge base to improve the answer relevance and accuracy. In real-world scenarios, beyond pure text, a substantial amount of knowledge is stored in tables, and user questions often require retrieving answers that are distributed across multiple tables. Retrieving knowledge from a table corpora (i.e., various individual tables) for a question remains nascent, for (i) how to understand intra- and inter-table knowledge effectively, (ii) how to filter unnecessary tables and retrieve the most relevant tables efficiently, (iii) how to organize complex retrieved contexts for LLMs’ reasoning, and (iv) how to evaluate the corresponding performance in a realistic setting. Facing the above challenges, in this paper, we first propose a table-corpora-aware RAG framework, named T-RAG, which consists of the hierarchical memory index, multistage retrieval, and graph-aware context organization for effective and efficient table knowledge retrieval and inference. Then, we develop a multi-table question answering benchmark named MultiTableQA, which spans 3 different task types, 57,193 tables, and 23,758 questions in total, and the sources are all from real-world scenarios. Based on MultiTableQA, we perform a comprehensive comparison of table retrieval methods, RAG-based approaches, and table-to-graph representation learning methods. T-RAG consistently achieves state-of-the-art accuracy, recall, and runtime performance, with improvements of up to 9.4%. Moreover, T-RAG yields an average inference gain of 11.8% across different downstream backbone LLMs. 

   more » « less
2. High Performance Data Engineering Everywhere

   https://doi.org/10.1109/SMDS49396.2020.00022  

   Widanage, Chathura; Perera, Niranda; Abeykoon, Vibhatha; Kamburugamuve, Supun; Kanewala, Thejaka Amila; Maithree, Hasara; Wickramasinghe, Pulasthi; Uyar, Ahmet; Gunduz, Gurhan; Fox, Geoffrey (October 2020, 2020 IEEE International Conference on Smart Data Services (SMDS))

   null (Ed.)

   The amazing advances being made in the fields of machine and deep learning are a highlight of the Big Data era for both enterprise and research communities. Modern applications require resources beyond a single node's ability to provide. However this is just a small part of the issues facing the overall data processing environment, which must also support a raft of data engineering for pre- and post-data processing, communication, and system integration. An important requirement of data analytics tools is to be able to easily integrate with existing frameworks in a multitude of languages, thereby increasing user productivity and efficiency. All this demands an efficient and highly distributed integrated approach for data processing, yet many of today's popular data analytics tools are unable to satisfy all these requirements at the same time. In this paper we present Cylon, an open-source high performance distributed data processing library that can be seamlessly integrated with existing Big Data and AI/ML frameworks. It is developed with a flexible C++ core on top of a compact data structure and exposes language bindings to C++, Java, and Python. We discuss Cylon's architecture in detail, and reveal how it can be imported as a library to existing applications or operate as a standalone framework. Initial experiments show that Cylon enhances popular tools such as Apache Spark and Dask with major performance improvements for key operations and better component linkages. Finally, we show how its design enables Cylon to be used cross-platform with minimum overhead, which includes popular AI tools such as PyTorch, Tensorflow, and Jupyter notebooks. 

   more » « less
3. Optimal Hashing in External Memory

   Conway, Alex Farach-Colton (January 2018, Leibniz international proceedings in informatics)

   Hash tables are a ubiquitous class of dictionary data structures. However, standard hash table implementations do not translate well into the external memory model, because they do not incorporate locality for insertions. Iacono and Pătraşu established an update/query tradeoff curve for external-hash tables: a hash table that performs insertions in O(λ/B) amortized IOs requires Ω(logλ N) expected IOs for queries, where N is the number of items that can be stored in the data structure, B is the size of a memory transfer, M is the size of memory, and λ is a tuning parameter. They provide a complicated hashing data structure, which we call the IP hash table, that meets this curve for λ that is Ω(loglogM +logM N). In this paper, we present a simpler external-memory hash table, the Bundle of Arrays Hash Table (BOA), that is optimal for a narrower range of λ. The simplicity of BOAs allows them to be readily modified to achieve the following results: A new external-memory data structure, the Bundle of Trees Hash Table (BOT), that matches the performance of the IP hash table, while retaining some of the simplicity of the BOAs. The Cache-Oblivious Bundle of Trees Hash Table (COBOT), the first cache-oblivious hash table. This data structure matches the optimality of BOTs and IP hash tables over the same range of λ. 

   more » « less
4. OPER: Optimality-Guided Embedding Table Parallelization for Large-scale Recommendation Model

   Wang, Zheng; Wang, Yuke; Feng, Boyuan; Huang, Guyue; Mudigere, Dheevatsa; Muthiah, Bharath; Li, Ang; Ding, Yufei (July 2024, USENIX Association)

   The deployment of Deep Learning Recommendation Models (DLRMs) involves the parallelization of extra-large embedding tables (EMTs) on multiple GPUs. Existing works overlook the input-dependent behavior of EMTs and parallelize them in a coarse-grained manner, resulting in unbalanced workload distribution and inter-GPU communication. To this end, we propose OPER, an algorithm-system co-design with OPtimality-guided Embedding table parallelization for large-scale Recommendation model training and inference. The core idea of OPER is to explore the connection between DLRM inputs and the efficiency of distributed EMTs, aiming to provide a near-optimal parallelization strategy for EMTs. Specifically, we conduct an in-depth analysis of various types of EMTs parallelism and propose a heuristic search algorithm to efficiently approximate an empirically near-optimal EMT parallelization. Furthermore, we implement a distributed shared memory-based system, which supports the lightweight but complex computation and communication pattern of fine-grained EMT parallelization, effectively converting theoretical improvements into real speedups. Extensive evaluation shows that OPER achieves 2.3× and 4.0× speedup on average in training and inference, respectively, over state-of-the-art DLRM frameworks. 

   more » « less
5. Kymatio: Scattering Transforms in Pyton

   Mathieu Andreux, Tomás Angles (January 2020, JMLR workshop and conference proceedings)

   null (Ed.)

   The wavelet scattering transform is an invariant and stable signal representation suitable for many signal processing and machine learning applications. We present the Kymatio software package, an easy-to-use, high-performance Python implementation of the scattering transform in 1D, 2D, and 3D that is compatible with modern deep learning frameworks, including PyTorch and TensorFlow/Keras. The transforms are implemented on both CPUs and GPUs, the latter offering a significant speedup over the former. The package also has a small memory footprint. Source code, documentation, and examples are available under a BSD license at https://www.kymat.io 

   more » « less