Related papers: A Distributed Learned Hash Table
Federated learning has gained popularity as a means of training models distributed across the wireless edge. The paper introduces delay-aware hierarchical federated learning (DFL) to improve the efficiency of distributed machine learning…
Motivated by the growing demand for serving large language model inference requests, we study distributed load balancing for global serving systems with network latencies. We consider a fluid model in which continuous flows of requests…
The increased use of Internet of Things (IoT) devices -- from basic sensors to robust embedded computers -- has boosted the demand for information processing and storing solutions closer to these devices. Edge computing has been established…
Embedding models have been an effective learning paradigm for high-dimensional data. However, one open issue of embedding models is that their representations (latent factors) often result in large parameter space. We observe that existing…
Locality-sensitive hashing (LSH) based frameworks have been used efficiently to select weight vectors in a dense hidden layer with high cosine similarity to an input, enabling dynamic pruning. While this type of scheme has been shown to…
Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data selection methods incur significant computational overhead, as…
Distributed multi-task learning (DMTL) effectively improves model generalization performance through the collaborative training of multiple related models. However, in large-scale learning scenarios, communication bottlenecks severely limit…
Deep neural networks (DNNs) exploit many layers and a large number of parameters to achieve excellent performance. The training process of DNN models generally handles large-scale input data with many sparse features, which incurs high…
Distributed frameworks are gaining increasingly widespread use in applications that process large amounts of data. One important example application is large scale similarity search, for which Locality Sensitive Hashing (LSH) has emerged as…
Querying graph data with low latency is an important requirement in application domains such as social networks and knowledge graphs. Graph queries perform multiple hops between vertices. When data is partitioned and stored across multiple…
The world needs diverse and unbiased data to train deep learning models. Currently data comes from a variety of sources that are unmoderated to a large extent. The outcomes of training neural networks with unverified data yields biased…
The expansion of edge computing has increased the attack surface, creating an urgent need for robust, real-time machine learning (ML)-based host intrusion detection systems (HIDS) that balance accuracy and efficiency. In such settings,…
Federated learning (FL) has been facilitating privacy-preserving deep learning in many walks of life such as medical image classification, network intrusion detection, and so forth. Whereas it necessitates a central parameter server for…
Recent advances in query optimization have shifted from traditional rule-based and cost-based techniques towards machine learning-driven approaches. Among these, reinforcement learning (RL) has attracted significant attention due to its…
The next-generation of wireless networks will enable many machine learning (ML) tools and applications to efficiently analyze various types of data collected by edge devices for inference, autonomy, and decision making purposes. However,…
With the advent of 5G networks and the rise of the Internet of Things (IoT), Content Delivery Networks (CDNs) are increasingly extending into the network edge. This shift introduces unique challenges, particularly due to the limited cache…
Deep Learning (DL) model-based AI services are increasingly offered in a variety of predictive analytics services such as computer vision, natural language processing, speech recognition. However, the quality of the DL models can degrade…
We address the joint problem of learning and scheduling in multi-hop wireless network without a prior knowledge on link rates. Previous scheduling algorithms need the link rate information, and learning algorithms often require a…
Diffusion-based planners have shown strong performance in short-horizon tasks but often fail in complex, long-horizon settings. We trace the failure to loose coupling between high-level (HL) sub-goal selection and low-level (LL) trajectory…
Transformer requires a fixed number of layers and heads which makes them inflexible to the complexity of individual samples and expensive in training and inference. To address this, we propose a sample-based Dynamic Hierarchical Transformer…