Related papers: Disaggregating Embedding Recommendation Systems wi…

Disaggregation modelling is a method of predicting disease risk at high resolution using aggregated response data. High resolution disease mapping is an important public health tool to aid the optimisation of resources, and is commonly used…

Deep learning-based models are utilized to achieve state-of-the-art performance for recommendation systems. A key challenge for these models is to work with millions of categorical classes or tokens. The standard approach is to learn…

Entity resolution (ER) is a fundamental task in data integration that enables insights from heterogeneous data sources. The primary challenge of ER lies in classifying record pairs as matches or nonmatches, which in multi-source ER (MS-ER)…

We consider electricity capacity expansion models, which optimize investment and retirement decisions by minimizing both investment and operation costs. In order to provide credible support for planning and policy decisions, these models…

Deep learning recommendation models have grown to the terabyte scale. Traditional serving schemes--that load entire models to a single server--are unable to support this scale. One approach to support this scale is with distributed serving,…

Disaggregated memory is a promising approach that addresses the limitations of traditional memory architectures by enabling memory to be decoupled from compute nodes and shared across a data center. Cloud platforms have deployed such…

Modern networked systems are increasingly reconfigurable, enabling demand-aware infrastructures whose resources can be adjusted according to the workload they currently serve. Such dynamic adjustments can be exploited to improve network…

Disaggregating the prefill and decoding phases represents an effective new paradigm for generative inference of large language models (LLM), which eliminates prefill-decoding interference and optimizes resource allocation. However, it is…

Federated fine-tuning offers a promising approach for tuning Large Language Models (LLMs) on edge devices while preserving data privacy. However, fine-tuning these models on edge devices remains challenging due to high memory,…

The mixture model is undoubtedly one of the greatest contributions to clustering. For continuous data, Gaussian models are often used and the Expectation-Maximization (EM) algorithm is particularly suitable for estimating parameters from…

We study the problem of learning similarity by using nonlinear embedding models (e.g., neural networks) from all possible pairs. This problem is well-known for its difficulty of training with the extreme number of pairs. For the special…

Segmentation has been a major task in neuroimaging. A large number of automated methods have been developed for segmenting healthy and diseased brain tissues. In recent years, deep learning techniques have attracted a lot of attention as a…

This paper describes how to augment techniques such as Distributed Shared Memory with recent trends on disaggregated Non Volatile Memory in the data centre so that the combination can be used in an edge environment with potentially volatile…

Deep learning recommendation systems serve personalized content under diverse tail-latency targets and input-query loads. In order to do so, state-of-the-art recommendation models rely on terabyte-scale embedding tables to learn user…

Centralized training methods have shown promising results in MR image reconstruction, but privacy concerns arise when gathering data from multiple institutions. Federated learning, a distributed collaborative training scheme, can utilize…

With the widespread adoption of large multimodal models, efficient inference across text, image, audio, and video modalities has become critical. However, existing multimodal inference systems typically employ monolithic architectures that…

Multimodal large language models (LLMs) empower LLMs to ingest inputs and generate outputs in multiple forms, such as text, image, and audio. However, the integration of multiple modalities introduces heterogeneity in both the model and…

The GEneral Matrix Multiplication (GEMM) is one of the essential algorithms in scientific computing. Single-thread GEMM implementations are well-optimised with techniques like blocking and autotuning. However, due to the complexity of…

Distributed decision problems features a group of agents that can only communicate over a peer-to-peer network, without a central memory. In applications such as network control and data ranking, each agent is only affected by a small…

With the explosive growth of Internet data, users are facing the problem of information overload, which makes it a challenge to efficiently obtain the required resources. Recommendation systems have emerged in this context. By filtering…