Related papers: CAFE: Towards Compact, Adaptive, and Fast Embeddin…

Low-dimensional representations, or embeddings, of a graph's nodes facilitate several practical data science and data engineering tasks. As such embeddings rely, explicitly or implicitly, on a similarity measure among nodes, they require…

Embedding learning is an important technique in deep recommendation models to map categorical features to dense vectors. However, the embedding tables often demand an extremely large number of parameters, which become the storage and…

Language models are increasingly adopting smaller architectures optimized for consumer devices. In this setting, inference efficiency is the primary constraint. Meanwhile, vocabulary sizes continue to grow rapidly, making the classification…

We discover a theoretical connection between explanation estimation and distribution compression that significantly improves the approximation of feature attributions, importance, and effects. While the exact computation of various machine…

Providing model-generated explanations in recommender systems is important to user experience. State-of-the-art recommendation algorithms - especially collaborative filtering (CF)-based approaches with shallow or deep models - usually work…

Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in…

Synthetic data generation has become an increasingly popular way of training models without the need for large, manually labeled datasets. For tasks like text embedding, synthetic data offers diverse and scalable training examples,…

Withtherapid advancement of large language models (LLMs), the context length for inference has been continuously increasing, leading to an exponential growth in the demand for Key-Value (KV) caching. This has resulted in a significant…

Deep learning technologies have demonstrated remarkable effectiveness in a wide range of tasks, and deep learning holds the potential to advance a multitude of applications, including in edge computing, where deep models are deployed on…

Diffusion-based image generation models excel at producing high-quality synthetic content, but suffer from slow and computationally expensive inference. Prior work has attempted to mitigate this by caching and reusing features within…

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…

Retrieval-augmented code generation often conditions the decoder on large retrieved code snippets. This ties online inference cost to repository size and introduces noise from long contexts. We present Hierarchical Embedding Fusion (HEF), a…

The goal of Feature Selection - comprising filter, wrapper, and embedded approaches - is to find the optimal feature subset for designated downstream tasks. Nevertheless, current feature selection methods are limited by: 1) the selection…

Edge caching and computing have been regarded as an efficient approach to tackle the wireless spectrum crunch problem. In this paper, we design a general coded caching with device computing strategy for content computation, e.g., virtual…

Federated learning (FL) is a machine learning paradigm that facilitates massively distributed model training with end-user data on edge devices directed by a central server. However, the large number of heterogeneous clients in FL…

Metric learning aims at learning a distance which is consistent with the semantic meaning of the samples. The problem is generally solved by learning an embedding for each sample such that the embeddings of samples of the same category are…

As large language models (LLMs) continue to advance, the demand for higher quality and faster processing of long contexts across various applications is growing. KV cache is widely adopted as it stores previously generated key and value…

Deep hashing retrieval has gained widespread use in big data retrieval due to its robust feature extraction and efficient hashing process. However, training advanced deep hashing models has become more expensive due to complex optimizations…

Explicit high-order feature interactions efficiently capture essential structural knowledge about the data of interest and have been used for constructing generative models. We present a supervised discriminative High-Order Parametric…

Recommendation systems are highly interested in technology companies nowadays. The businesses are constantly growing users and products, causing the number of users and items to continuously increase over time, to very large numbers.…