English
Related papers

Related papers: Applying SoftTriple Loss for Supervised Language M…

200 papers

Large language models (LLMs) have been garnering increasing attention in the recommendation community. Some studies have observed that LLMs, when fine-tuned by the cross-entropy (CE) loss with a full softmax, could achieve…

Information Retrieval · Computer Science 2024-08-27 Cong Xu , Zhangchi Zhu , Mo Yu , Jun Wang , Jianyong Wang , Wei Zhang

We employ triplet loss as a feature embedding regularizer to boost classification performance. Standard architectures, like ResNet and Inception, are extended to support both losses with minimal hyper-parameter tuning. This promotes…

Computer Vision and Pattern Recognition · Computer Science 2020-03-03 Ahmed Taha , Yi-Ting Chen , Teruhisa Misu , Abhinav Shrivastava , Larry Davis

With the increasing complexity of the traffic environment, the significance of safety perception in intelligent driving is intensifying. Traditional methods in the field of intelligent driving perception rely on deep learning, which suffers…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Haobo Yang , Shiyan Zhang , Zhuoyi Yang , Xinyu Zhang , Jilong Guo , Zongyou Yang , Jun Li

Sparse autoencoders (SAEs) are widely used for interpreting language model activations. A key evaluation metric is the increase in cross-entropy loss between the original model logits and the reconstructed model logits when replacing model…

Machine Learning · Computer Science 2025-04-01 Adam Karvonen

All machine learning algorithms use a loss, cost, utility or reward function to encode the learning objective and oversee the learning process. This function that supervises learning is a frequently unrecognized hyperparameter that…

Neural and Evolutionary Computing · Computer Science 2024-11-06 Mathew Mithra Noel , Arindam Banerjee , Yug Oswal , Geraldine Bessie Amali D , Venkataraman Muthiah-Nakarajan

Deep learning has been shown to achieve impressive results in several domains like computer vision and natural language processing. A key element of this success has been the development of new loss functions, like the popular cross-entropy…

Machine Learning · Computer Science 2019-07-19 Francesco Giannini , Giuseppe Marra , Michelangelo Diligenti , Marco Maggini , Marco Gori

In this work, we propose to study the performance of a model trained with a sentence embedding regression loss component for the Automated Audio Captioning task. This task aims to build systems that can describe audio content with a single…

Sound · Computer Science 2023-05-03 Etienne Labbé , Julien Pinquier , Thomas Pellegrini

Deep learning-based models generalize better to unknown data samples after being guided "where to look" by incorporating human perception into training strategies. We made an observation that the entropy of the model's salience trained in…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Jacob Piland , Adam Czajka , Christopher Sweet

The effectiveness of large language models (LLMs) is often hindered by duplicated data in their extensive pre-training datasets. Current approaches primarily focus on detecting and removing duplicates, which risks the loss of valuable…

Computation and Language · Computer Science 2024-07-10 Nan He , Weichen Xiong , Hanwen Liu , Yi Liao , Lei Ding , Kai Zhang , Guohua Tang , Xiao Han , Wei Yang

During the finetuning stage of text generation tasks, standard cross-entropy loss treats all tokens equally. This can lead models to overemphasize high-frequency, low-information tokens, neglecting lower-frequency tokens crucial for…

Computation and Language · Computer Science 2025-06-10 Jintian Shao

Recently, fine-tuning pre-trained language models (e.g., multilingual BERT) to downstream cross-lingual tasks has shown promising results. However, the fine-tuning process inevitably changes the parameters of the pre-trained model and…

Computation and Language · Computer Science 2020-10-06 Zihan Liu , Genta Indra Winata , Andrea Madotto , Pascale Fung

The learning objective is integral to collaborative filtering systems, where the Bayesian Personalized Ranking (BPR) loss is widely used for learning informative backbones. However, BPR often experiences slow convergence and suboptimal…

Information Retrieval · Computer Science 2024-06-25 Xiaodong Yang , Huiyuan Chen , Yuchen Yan , Yuxin Tang , Yuying Zhao , Eric Xu , Yiwei Cai , Hanghang Tong

Distance Metric Learning (DML) has attracted much attention in image processing in recent years. This paper analyzes its impact on supervised fine-tuning language models for Natural Language Processing (NLP) classification tasks under…

Computation and Language · Computer Science 2022-11-29 Witold Sosnowski , Anna Wróblewska , Karolina Seweryn , Piotr Gawrysiak

Accurately modeling idiomatic or non-compositional language has been a longstanding challenge in Natural Language Processing (NLP). This is partly because these expressions do not derive their meanings solely from their constituent words,…

Computation and Language · Computer Science 2024-09-06 Wei He , Marco Idiart , Carolina Scarton , Aline Villavicencio

We propose a method to optimize language model pre-training data mixtures through efficient approximation of the cross-entropy loss corresponding to each candidate mixture via a Mixture of Data Experts (MDE). We use this approximation as a…

Machine Learning · Computer Science 2025-02-25 Lior Belenki , Alekh Agarwal , Tianze Shi , Kristina Toutanova

This paper describes one objective function for learning semantically coherent feature embeddings in multi-output classification problems, i.e., when the response variables have dimension higher than one. In particular, we consider the…

Computer Vision and Pattern Recognition · Computer Science 2020-03-23 Hugo Proença , Ehsan Yaghoubi , Pendar Alirezazadeh

As language models grow ever larger, so do their vocabularies. This has shifted the memory footprint of LLMs during training disproportionately to one single layer: the cross-entropy in the loss computation. Cross-entropy builds up a logit…

Machine Learning · Computer Science 2025-03-12 Erik Wijmans , Brody Huval , Alexander Hertzberg , Vladlen Koltun , Philipp Krähenbühl

We propose a simple modification from a fixed margin triplet loss to an adaptive margin triplet loss. While the original triplet loss is used widely in classification problems such as face recognition, face re-identification and…

Computer Vision and Pattern Recognition · Computer Science 2021-07-14 Mai Lan Ha , Volker Blanz

When incrementally trained on new classes, deep neural networks are subject to catastrophic forgetting which leads to an extreme deterioration of their performance on the old classes while learning the new ones. Using a small memory…

Machine Learning · Computer Science 2022-11-15 Quentin Jodelet , Xin Liu , Tsuyoshi Murata

As an effective way of metric learning, triplet loss has been widely used in many deep learning tasks, including face recognition and person-ReID, leading to many states of the arts. The main innovation of triplet loss is using feature map…

Machine Learning · Computer Science 2017-11-15 Gongze Cao , Yezhou Yang , Jie Lei , Cheng Jin , Yang Liu , Mingli Song