Related papers: ConFit: Improving Resume-Job Matching using Data A…

Learning representations that transfer well to diverse downstream tasks remains a central challenge in representation learning. Existing paradigms -- contrastive learning, self-supervised masking, and denoising auto-encoders -- balance this…

Large language models (LLMs) are increasingly being deployed in high-stakes applications like hiring, yet their potential for unfair decision-making remains understudied in generative and retrieval settings. In this work, we examine the…

How can neural networks trained by contrastive learning extract features from the unlabeled data? Why does contrastive learning usually need much stronger data augmentations than supervised learning to ensure good representations? These…

Inspired by the idea of Positive-incentive Noise (Pi-Noise or $\pi$-Noise) that aims at learning the reliable noise beneficial to tasks, we scientifically investigate the connection between contrastive learning and $\pi$-noise in this…

Contrastive learning is among the most successful methods for visual representation learning, and its performance can be further improved by jointly performing clustering on the learned representations. However, existing methods for joint…

This paper proposes a cold start recommendation model that integrates contrastive learning, aiming to solve the problem of performance degradation of recommendation systems in cold start scenarios due to the scarcity of user and item…

We study generating abstractive summaries that are faithful and factually consistent with the given articles. A novel contrastive learning formulation is presented, which leverages both reference summaries, as positive training data, and…

Personalized and content-adaptive image enhancement can find many applications in the age of social media and mobile computing. This paper presents a relative-learning-based approach, which, unlike previous methods, does not require…

Contrastive learning has been shown to produce generalizable representations of audio and visual data by maximizing the lower bound on the mutual information (MI) between different views of an instance. However, obtaining a tight lower…

Inspired by the impressive success of contrastive learning (CL), a variety of graph augmentation strategies have been employed to learn node representations in a self-supervised manner. Existing methods construct the contrastive samples by…

Deep image matting methods have achieved increasingly better results on benchmarks (e.g., Composition-1k/alphamatting.com). However, the robustness, including robustness to trimaps and generalization to images from different domains, is…

Large-scale pre-trained models such as CodeBERT, GraphCodeBERT have earned widespread attention from both academia and industry. Attributed to the superior ability in code representation, they have been further applied in multiple…

Contrastive learning between different views of the data achieves outstanding success in the field of self-supervised representation learning and the learned representations are useful in broad downstream tasks. Since all supervision…

Although synthetic data has changed various aspects of information retrieval (IR) pipelines, the main training paradigm remains: contrastive learning with binary relevance labels, where one positive document is compared against several…

Large language models (LLMs) have demonstrated remarkable capabilities across various research domains, including the field of Information Retrieval (IR). However, the responses generated by off-the-shelf LLMs tend to be generic, i.e.,…

Relation Extraction (RE) is a pivotal task in automatically extracting structured information from unstructured text. In this paper, we present a multi-faceted approach that integrates representative examples and through co-set expansion.…

We present a novel semi-supervised learning framework that intelligently leverages the consistency regularization between the model's predictions from two strongly-augmented views of an image, weighted by a confidence of pseudo-label,…

In web search, typically a candidate generation step selects a small set of documents---from collections containing as many as billions of web pages---that are subsequently ranked and pruned before being presented to the user. In Bing, the…

This paper presents a comprehensive study on resume classification to reduce the time and labor needed to screen an overwhelming number of applications significantly, while improving the selection of suitable candidates. A total of 6,492…

Self-training and contrastive learning have emerged as leading techniques for incorporating unlabeled data, both under distribution shift (unsupervised domain adaptation) and when it is absent (semi-supervised learning). However, despite…