English
Related papers

Related papers: KNN-BERT: Fine-Tuning Pre-Trained Models with KNN …

200 papers

Nearest neighbor-based methods are commonly used for classification tasks and as subroutines of other data-analysis methods. An attacker with the capability of inserting their own data points into the training set can manipulate the…

Machine Learning · Computer Science 2022-08-16 Ara Vartanian , Will Rosenbaum , Scott Alfeld

Finetuning a pretrained model has become a standard approach for training neural networks on novel tasks, resulting in fast convergence and improved performance. In this work, we study an alternative finetuning method, where instead of…

Machine Learning · Computer Science 2023-07-04 Gal Kaplun , Andrey Gurevich , Tal Swisa , Mazor David , Shai Shalev-Shwartz , Eran Malach

Knowledge tracing---where a machine models the knowledge of a student as they interact with coursework---is a well established problem in computer supported education. Though effectively modeling student knowledge would have high…

Artificial Intelligence · Computer Science 2015-06-22 Chris Piech , Jonathan Spencer , Jonathan Huang , Surya Ganguli , Mehran Sahami , Leonidas Guibas , Jascha Sohl-Dickstein

Language models (LMs) pretrained on a large text corpus and fine-tuned on a downstream text corpus and fine-tuned on a downstream task becomes a de facto training strategy for several natural language processing (NLP) tasks. Recently, an…

Computation and Language · Computer Science 2021-07-23 Junghoon Lee , Jounghee Kim , Pilsung Kang

This paper describes ANN-Benchmarks, a tool for evaluating the performance of in-memory approximate nearest neighbor algorithms. It provides a standard interface for measuring the performance and quality achieved by nearest neighbor…

Information Retrieval · Computer Science 2018-07-19 Martin Aumüller , Erik Bernhardsson , Alexander Faithfull

Recent studies of large-scale contrastive pretraining in the text embedding domain show that using single-source minibatches, rather than mixed-source minibatches, can substantially improve overall model accuracy. In this work, we explore…

Machine Learning · Computer Science 2024-07-29 Luke Merrick

Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing…

Computation and Language · Computer Science 2020-02-06 Chi Sun , Xipeng Qiu , Yige Xu , Xuanjing Huang

Recent works show that learning contextualized embeddings for words is beneficial for downstream tasks. BERT is one successful example of this approach. It learns embeddings by solving two tasks, which are masked language model (masked LM)…

Computation and Language · Computer Science 2020-11-10 Çağla Aksoy , Alper Ahmetoğlu , Tunga Güngör

Pretrained language models have achieved state-of-the-art performance when adapted to a downstream NLP task. However, theoretical analysis of these models is scarce and challenging since the pretraining and downstream tasks can be very…

Machine Learning · Computer Science 2022-04-22 Colin Wei , Sang Michael Xie , Tengyu Ma

Reinforcement learning systems require good representations to work well. For decades practical success in reinforcement learning was limited to small domains. Deep reinforcement learning systems, on the other hand, are scalable, not…

Machine Learning · Computer Science 2020-03-18 Sina Ghiassian , Banafsheh Rafiee , Yat Long Lo , Adam White

Traditional deep learning models implicity encode knowledge limiting their transparency and ability to adapt to data changes. Yet, this adaptability is vital for addressing user data privacy concerns. We address this limitation by storing…

Computer Vision and Pattern Recognition · Computer Science 2024-02-21 Sebastian Doerrich , Tobias Archut , Francesco Di Salvo , Christian Ledig

Named Entity Recognition (NER) frequently suffers from the problem of insufficient labeled data, particularly in fine-grained NER scenarios. Although $K$-shot learning techniques can be applied, their performance tends to saturate when the…

Computation and Language · Computer Science 2023-11-14 Su Ah Lee , Seokjin Oh , Woohwan Jung

It has become standard to solve NLP tasks by fine-tuning pre-trained language models (LMs), especially in low-data settings. There is minimal theoretical understanding of empirical success, e.g., why fine-tuning a model with $10^8$ or more…

Machine Learning · Computer Science 2023-06-07 Sadhika Malladi , Alexander Wettig , Dingli Yu , Danqi Chen , Sanjeev Arora

The highly non-linear nature of deep neural networks causes them to be susceptible to adversarial examples and have unstable gradients which hinders interpretability. However, existing methods to solve these issues, such as adversarial…

Machine Learning · Computer Science 2023-01-11 Suraj Srinivas , Kyle Matoba , Himabindu Lakkaraju , Francois Fleuret

The performance of machine learning models often relies on large labeled datasets; however, data collected from diverse sources can contain label noise. Recent work has shown that, in noisy settings, there may exist a subset of the training…

Machine Learning · Computer Science 2026-05-05 Kumar Shubham , Pavan Karjol , Kiran M K , Prathosh AP

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks(GNNs) have emerged as a powerful tool for graph…

Machine Learning · Computer Science 2023-02-28 Zemin Liu , Xingtong Yu , Yuan Fang , Xinming Zhang

Demands for minimum parameter setup in machine learning models are desirable to avoid time-consuming optimization processes. The $k$-Nearest Neighbors is one of the most effective and straightforward models employed in numerous problems.…

Machine Learning · Computer Science 2022-10-03 Danilo Samuel Jodas , Leandro Aparecido Passos , Ahsan Adeel , João Paulo Papa

In recent years, deep learning techniques have been introduced into the field of trajectory optimization to improve convergence and speed. Training such models requires large trajectory datasets. However, the convergence of low thrust (LT)…

Optimization and Control · Mathematics 2022-02-11 Ruida Xie , Andrew G. Dempster

Alignment between image and text has shown promising improvements on patch-level pre-trained document image models. However, investigating more effective or finer-grained alignment techniques during pre-training requires a large amount of…

Computer Vision and Pattern Recognition · Computer Science 2022-12-02 Lei Wang , Jiabang He , Xing Xu , Ning Liu , Hui Liu

In recent years, representation learning approaches have disrupted many multimedia computing tasks. Among those approaches, deep convolutional neural networks (CNNs) have notably reached human level expertise on some constrained image…

Computer Vision and Pattern Recognition · Computer Science 2019-10-01 Lucas Pascal , Xavier Bost , Benoît Huet