相关论文: Matching-oriented Product Quantization For Ad-hoc …

Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting. Contrastive learning has recently shown its promising representation learning capability in…

Image retrieval methods that employ hashing or vector quantization have achieved great success by taking advantage of deep learning. However, these approaches do not meet expectations unless expensive label information is sufficient. To…

Recently, many software tools have been developed to perform quantification in LC-MS analyses. However, most of them are specific to either a quantification strategy (e.g. label-free or isotopic labelling) or a mass-spectrometry system…

Real-time object detection plays a vital role in various computer vision applications. However, deploying real-time object detectors on resource-constrained platforms poses challenges due to high computational and memory requirements. This…

Supervised contrastive learning has achieved remarkable success by leveraging label information; however, determining positive samples in multi-label scenarios remains a critical challenge. In multi-label supervised contrastive learning…

Embedding high-dimensional data into resource-limited quantum devices remains a significant challenge for practical quantum machine learning. In multimodal face anti-spoofing, while linear compression methods such as principal component…

It is critical to deploy complicated neural network models on hardware with limited resources. This paper proposes a novel model quantization method, named the Low-Cost Proxy-Based Adaptive Mixed-Precision Model Quantization (LCPAQ), which…

In order to deploy deep models in a computationally efficient manner, model quantization approaches have been frequently used. In addition, as new hardware that supports mixed bitwidth arithmetic operations, recent research on mixed…

Mixture of autoregressions (MoAR) models provide a model-based approach to the clustering of time series data. The maximum likelihood (ML) estimation of MoAR models requires the evaluation of products of large numbers of densities of normal…

Multi-target regression is concerned with the prediction of multiple continuous target variables using a shared set of predictors. Two key challenges in multi-target regression are: (a) modelling target dependencies and (b) scalability to…

By summarizing longer consumer health questions into shorter and essential ones, medical question-answering systems can more accurately understand consumer intentions and retrieve suitable answers. However, medical question summarization is…

Recently, contrastive learning (CL) plays an important role in exploring complementary information for multi-view clustering (MVC) and has attracted increasing attention. Nevertheless, real-world multi-view data suffer from data…

Parameter quantization for Large Language Models (LLMs) has attracted increasing attentions recently in reducing memory costs and improving computational efficiency. Early approaches have been widely adopted. However, the existing methods…

Post-training of LLMs with RLHF, and subsequently preference optimization algorithms such as DPO, IPO, etc., made a big difference in improving human alignment. However, all such techniques can only work with a single (human) objective. In…

Prior authorization (PA) requires interpretation of complex and fragmented coverage policies, yet existing retrieval-augmented systems rely on static top-$K$ strategies with fixed numbers of retrieved sections. Such fixed retrieval can be…

This paper suggests the use of projective clustering based product quantization for improving nearest neighbor and max-inner-product vector search (MIPS) algorithms. We provide anisotropic and quantized variants of projective clustering…

The ever-growing computational complexity of Large Language Models (LLMs) necessitates efficient deployment strategies. The current state-of-the-art approaches for Post-training Quantization (PTQ) often require calibration to achieve the…

Multilabel representation learning is recognized as a challenging problem that can be associated with either label dependencies between object categories or data-related issues such as the inherent imbalance of positive/negative samples.…

The Quality-Diversity (QD) optimization aims to discover a collection of high-performing solutions that simultaneously exhibit diverse behaviors within a user-defined behavior space. This paradigm has stimulated significant research…

We propose a quantization based approach for fast approximate Maximum Inner Product Search (MIPS). Each database vector is quantized in multiple subspaces via a set of codebooks, learned directly by minimizing the inner product quantization…