English
Related papers

Related papers: Faster and Memory-Efficient Training of Sequential…

200 papers

Cross Entropy (CE) has an important role in machine learning and, in particular, in neural networks. It is commonly used in neural networks as the cost between the known distribution of the label and the Softmax/Sigmoid output. In this…

Machine Learning · Computer Science 2020-07-17 Ron Shoham , Haim Permuter

A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on a given pretext task such as instance discrimination. In…

Computer Vision and Pattern Recognition · Computer Science 2022-10-21 Xin Liu , Zhongdao Wang , Yali Li , Shengjin Wang

Adversarial robustness has emerged as an important topic in deep learning as carefully crafted attack samples can significantly disturb the performance of a model. Many recent methods have proposed to improve adversarial robustness by…

Machine Learning · Computer Science 2019-08-08 Hao-Yun Chen , Jhao-Hong Liang , Shih-Chieh Chang , Jia-Yu Pan , Yu-Ting Chen , Wei Wei , Da-Cheng Juan

Pushing forward the compute efficacy frontier in deep learning is critical for tasks that require frequent model re-training or workloads that entail training a large number of models. We introduce SliceOut -- a dropout-inspired scheme…

Machine Learning · Computer Science 2021-04-02 Pascal Notin , Aidan N. Gomez , Joanna Yoo , Yarin Gal

Real-world applications require the classification model to adapt to new classes without forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a model with limited memory size to meet this requirement. Typical…

Machine Learning · Computer Science 2023-02-17 Da-Wei Zhou , Qi-Wei Wang , Han-Jia Ye , De-Chuan Zhan

Task-incremental continual learning refers to continually training a model in a sequence of tasks while overcoming the problem of catastrophic forgetting (CF). The issue arrives for the reason that the learned representations are forgotten…

Machine Learning · Computer Science 2023-05-23 Yun Luo , Xiaotian Lin , Zhen Yang , Fandong Meng , Jie Zhou , Yue Zhang

Large Language Models (LLMs) typically rely on Supervised Fine-Tuning (SFT) to specialize in downstream tasks, with the Cross Entropy (CE) loss being the de facto choice. However, CE maximizes the likelihood of observed data without…

Machine Learning · Computer Science 2025-04-08 Ziniu Li , Congliang Chen , Tian Xu , Zeyu Qin , Jiancong Xiao , Zhi-Quan Luo , Ruoyu Sun

Although prevailing supervised and self-supervised learning augmented sequential recommendation (SeRec) models have achieved improved performance with powerful neural network architectures, we argue that they still suffer from two…

Information Retrieval · Computer Science 2025-02-14 Xinping Zhao , Baotian Hu , Yan Zhong , Shouzheng Huang , Zihao Zheng , Meng Wang , Haofen Wang , Min Zhang

Negative sampling (NS) loss plays an important role in learning knowledge graph embedding (KGE) to handle a huge number of entities. However, the performance of KGE degrades without hyperparameters such as the margin term and number of…

Machine Learning · Computer Science 2022-07-08 Hidetaka Kamigaito , Katsuhiko Hayashi

The accurate representation of variable renewable generation (RES, e.g., wind, solar PV) assets in capacity expansion planning (CEP) studies is paramount to capture spatial and temporal correlations that may exist between sites and impact…

Systems and Control · Electrical Eng. & Systems 2021-04-14 David Radu , Antoine Dubois , Mathias Berger , Damien Ernst

This paper develops a memory-efficient approach for Sequential Pattern Mining (SPM), a fundamental topic in knowledge discovery that faces a well-known memory bottleneck for large data sets. Our methodology involves a novel hybrid trie data…

Databases · Computer Science 2024-07-30 Amin Hosseininasab , Willem-Jan van Hoeve , Andre A. Cire

The sequential recommendation aims to recommend items, such as products, songs and places, to users based on the sequential patterns of their historical records. Most existing sequential recommender models consider the next item prediction…

Information Retrieval · Computer Science 2021-09-14 Ruihong Qiu , Zi Huang , Hongzhi Yin

The cross-entropy (CE) method is simple and versatile technique for optimization, based on Kullback-Leibler (or cross-entropy) minimization. The method can be applied to a wide range of optimization tasks, including continuous, discrete,…

Computation · Statistics 2015-03-09 Tim Benham , Qibin Duan , Dirk P. Kroese , Benoit Liquet

In real-world applications, dynamic scenarios require the models to possess the capability to learn new tasks continuously without forgetting the old knowledge. Experience-Replay methods store a subset of the old images for joint training.…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Xinyuan Gao , Songlin Dong , Yuhang He , Xing Wei , Yihong Gong

Although deep learning has demonstrated remarkable capability in learning from unstructured data, modern tree-based ensemble models remain superior in extracting relevant information and learning from structured datasets. While several…

Machine Learning · Computer Science 2026-02-05 Yi-Chun Liao , Chieh-Lin Tsai , Yuan-Hao Chang , Camélia Slimani , Jalil Boukhobza , Tei-Wei Kuo

The rapid growth of dataset scales has been a key driver in advancing deep learning research. However, as dataset scale increases, the training process becomes increasingly inefficient due to the presence of low-value samples, including…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Qing Zhou , Junyu Gao , Qi Wang

This paper introduces a novel perspective to significantly mitigate catastrophic forgetting in continuous learning (CL), which emphasizes models' capacity to preserve existing knowledge and assimilate new information. Current replay-based…

Machine Learning · Computer Science 2024-04-10 Jianshu Zhang , Yankai Fu , Ziheng Peng , Dongyu Yao , Kun He

Even though machine learning (ML) techniques are being widely used in communications, the question of how to train communication systems has received surprisingly little attention. In this paper, we show that the commonly used binary…

Information Theory · Computer Science 2023-03-08 Reinhard Wiesmayr , Gian Marti , Chris Dick , Haochuan Song , Christoph Studer

We study classifiers operating under severe classification time constraints, corresponding to 1-1000 CPU microseconds, using Convolutional Tables Ensemble (CTE), an inherently fast architecture for object category recognition. The…

Computer Vision and Pattern Recognition · Computer Science 2016-02-16 Aharon Bar-Hillel , Eyal Krupka , Noam Bloom

In modern recommender systems, CTR/CVR models are increasingly trained with ranking objectives to improve item ranking quality. While this shift aligns training more closely with serving goals, most existing methods rely on in-batch…

Information Retrieval · Computer Science 2025-06-17 YaChen Yan , Liubo Li , Ravi Choudhary
‹ Prev 1 3 4 5 6 7 10 Next ›