Related papers: Learning Multi-dimensional Indexes
Reinforcement learning has emerged as a promising paradigm for aligning diffusion and flow-matching models with human preferences, yet practitioners face fragmented codebases, model-specific implementations, and engineering complexity. We…
Flow matching has emerged as a powerful generative framework, with recent few-step methods achieving remarkable inference acceleration. However, we identify a critical yet overlooked limitation: these models suffer from severe diversity…
Large Language Models (LLMs) have a natural role in answering complex queries about data streams, but the high computational cost of LLM inference makes them infeasible in many such tasks. We propose online cascade learning, the first…
In this paper, we propose Multi-Modal Databases (MMDBs), which is a new class of database systems that can seamlessly query text and tables using SQL. To enable seamless querying of textual data using SQL in an MMDB, we propose to extend…
Existing learned indexes (e.g., RMI, ALEX, PGM) optimize the internal regressor of each node, not the overall structure such as index height, the size of each layer, etc. In this paper, we share our recent findings that we can achieve…
The amount of data in our society has been exploding in the era of big data today. In this paper, we address several open challenges of big data stream classification, including high volume, high velocity, high dimensionality, high…
Machine Learning (ML) techniques have been successfully applied to design various learned database index structures for both the one- and multi-dimensional spaces. Particularly, a class of traditional multi-dimensional indexes has been…
Convolutional networks are at the center of best-in-class computer vision applications for a wide assortment of undertakings. Since 2014, a profound amount of work began to make better convolutional architectures, yielding generous…
With the rising quantity of textual data available in electronic format, the need to organize it become a highly challenging task. In the present paper, we explore a document organization framework that exploits an intelligent hierarchical…
The large size and fast growth of data repositories, such as data lakes, has spurred the need for data discovery to help analysts find related data. The problem has become challenging as (i) a user typically does not know what datasets…
The data stream model has been defined for new classes of applications involving massive data being generated at a fast pace. Web click stream analysis and detection of network intrusions are two examples. Cluster analysis on data streams…
Floods are among the most destructive natural disasters, which are highly complex to model. The research on the advancement of flood prediction models contributed to risk reduction, policy suggestion, minimization of the loss of human life,…
To stay competitive in today's data driven economy, enterprises large and small are turning to stream processing platforms to process high volume, high velocity, and diverse streams of data (fast data) as they arrive. Low-level programming…
Various modifications of decision trees have been extensively used during the past years due to their high efficiency and interpretability. Tree node splitting based on relevant feature selection is a key step of decision tree learning, at…
Time-evolving stream datasets exist ubiquitously in many real-world applications where their inherent hot keys often evolve over times. Nevertheless, few existing solutions can provide efficient load balance on these time-evolving datasets…
Sequential learning in deep models often suffers from challenges such as catastrophic forgetting and loss of plasticity, largely due to the permutation dependence of gradient-based algorithms, where the order of training data impacts the…
The current flood of information in all areas of machine learning research, from computer vision to reinforcement learning, has made it difficult to make aggregate scientific inferences. It can be challenging to distill a myriad of similar…
Switching, routing, and security functions are the backbone of packet processing networks. Fast and efficient processing of packets requires maintaining the state of a large number of transient network connections. In particular, modern…
We present FLINT (learning-based FLow estimation and temporal INTerpolation), a novel deep learning-based approach to estimate flow fields for 2D+time and 3D+time scientific ensemble data. FLINT can flexibly handle different types of…
This paper deals with the query problem in the Internet of Things (IoT). Flooding is an important query strategy. However, original flooding is prone to cause heavy network loads. To address this problem, we propose a variant of flooding,…