Related papers: The Case for Learned In-Memory Joins

Embedding fusion has emerged as an effective approach for enhancing performance across various NLP tasks. However, systematic guidelines for selecting optimal layers and developing effective fusion strategies for the integration of LLMs…

Joint machine learning models that allow synthesizing and classifying data often offer uneven performance between those tasks or are unstable to train. In this work, we depart from a set of empirical observations that indicate the…

Scanning and filtering over multi-dimensional tables are key operations in modern analytical database engines. To optimize the performance of these operations, databases often create clustered indexes over a single dimension or…

The main purpose of incremental learning is to learn new knowledge while not forgetting the knowledge which have been learned before. At present, the main challenge in this area is the catastrophe forgetting, namely the network will lose…

Model merging is an effective strategy to merge multiple models for enhancing model performances, and more efficient than ensemble learning as it will not introduce extra computation into inference. However, limited research explores if the…

Join order selection is a sub-field of query optimization that aims to find the optimal join order for an SQL query with the minimum cost. The challenge lies in the exponentially growing search space as the number of tables increases,…

Federated Learning is an emerging distributed collaborative learning paradigm used by many of applications nowadays. The effectiveness of federated learning relies on clients' collective efforts and their willingness to contribute local…

Explicitly modelling field interactions and correlations in complex document structures has recently gained popularity in neural document embedding and retrieval tasks. Although this requires the specification of bespoke task-dependent…

Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…

Convolutional Neural Networks (CNNs) are used to evaluate accelerometer and microphone data for bearing and induction motor diagnosis. A Long Short-Term Memory (LSTM) recurrent neural network is used to combine sensor information…

Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this…

Multi-instance learning (MIL) is a widely-applied technique in practical applications that involve complex data structures. MIL can be broadly categorized into two types: traditional methods and those based on deep learning. These…

Tool-augmented language models, equipped with retrieval, memory, or external APIs, are reshaping AI, yet their theoretical advantages remain underexplored. In this paper, we address this question by demonstrating the benefits of in-tool…

Research on learned cardinality estimation has made significant progress in recent years. However, existing methods still face distinct challenges that hinder their practical deployment in production environments. We define these challenges…

Deep neural networks (DNNs) often suffer from "catastrophic forgetting" during incremental learning (IL) --- an abrupt degradation of performance on the original set of classes when the training objective is adapted to a newly added set of…

This paper considers deep visual recognition on long-tailed data. To be general, we consider two applied scenarios, \ie, deep classification and deep metric learning. Under the long-tailed data distribution, the majority classes (\ie, tail…

Humans can learn concepts or recognize items from just a handful of examples, while machines require many more samples to perform the same task. In this paper, we build a computational model to investigate the possibility of this kind of…

Recent years, the database committee has attempted to develop automatic database management systems. Although some researches show that the applying AI to data management is a significant and promising direction, there still exists many…

The technology of dynamic map fusion among networked vehicles has been developed to enlarge sensing ranges and improve sensing accuracies for individual vehicles. This paper proposes a federated learning (FL) based dynamic map fusion…

The recursive model index (RMI) has recently been introduced as a machine-learned replacement for traditional indexes over sorted data, achieving remarkably fast lookups. Follow-up work focused on explaining RMI's performance and…