Related papers: Accelerated Convergence for Counterfactual Learnin…

Learning to rank (LTR) is widely employed in web searches to prioritize pertinent webpages from retrieved content based on input queries. However, traditional LTR models encounter two principal obstacles that lead to suboptimal performance:…

In decentralized learning, a network of nodes cooperate to minimize an overall objective function that is usually the finite-sum of their local objectives, and incorporates a non-smooth regularization term for the better generalization…

Language models contain ranking-based knowledge and are powerful solvers of in-context ranking tasks. For instance, they may have parametric knowledge about the ordering of countries by size or may be able to rank product reviews by…

Reinforcement learning (RL) algorithms usually require a substantial amount of interaction data and perform well only for specific tasks in a fixed environment. In some scenarios such as healthcare, however, usually only few records are…

User modeling, which aims to capture users' characteristics or interests, heavily relies on task-specific labeled data and suffers from the data sparsity issue. Several recent studies tackled this problem by pre-training the user model on…

Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams by deriving pseudo-rewards from majority voting consensus. However, existing TTRL methods rely…

Reciprocal recommender systems (RRS) in dating, gaming, and talent platforms require mutual acceptance for a match. Logged data, however, over-represents popular profiles due to past exposure policies, creating feedback loops that skew…

Contrastive Learning (CL) has recently emerged as a powerful technique in recommendation systems, particularly for its capability to harness self-supervised signals from perturbed views to mitigate the persistent challenge of data sparsity.…

Recently, contrastive learning has achieved great results in self-supervised learning, where the main idea is to push two augmentations of an image (positive pairs) closer compared to other random images (negative pairs). We argue that not…

The performance of stochastic gradient descent (SGD) depends critically on how learning rates are tuned and decreased over time. We propose a method to automatically adjust multiple learning rates so as to minimize the expected error at any…

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most of methods mainly focus on the instance level information…

In this paper, we consider a problem of learning supervised PageRank models, which can account for some properties not considered by classical approaches such as the classical PageRank algorithm. Due to huge hidden dimension of the…

Stochastic gradient descent (SGD) is a workhorse algorithm for solving large-scale optimization problems in data science and machine learning. Understanding the convergence of SGD is hence of fundamental importance. In this work we examine…

Contrastive Self-supervised Learning (CSL) is a practical solution that learns meaningful visual representations from massive data in an unsupervised approach. The ordinary CSL embeds the features extracted from neural networks onto…

Information Retrieval (IR) systems used in search and recommendation platforms frequently employ Learning-to-Rank (LTR) models to rank items in response to user queries. These models heavily rely on features derived from user interactions,…

Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization. However, its training procedure suffers from confirmation bias due to the noise contained in self-generated artificial labels. Moreover,…

While SGD, which samples from the data with replacement is widely studied in theory, a variant called Random Reshuffling (RR) is more common in practice. RR iterates through random permutations of the dataset and has been shown to converge…

Applying Differentially Private Stochastic Gradient Descent (DPSGD) to training modern, large-scale neural networks such as transformer-based models is a challenging task, as the magnitude of noise added to the gradients at each iteration…

We study counterfactual regression, which aims to map input features to outcomes under hypothetical scenarios that differ from those observed in the data. This is particularly useful for decision-making when adapting to sudden shifts in…

Stance detection classifies stance relations (namely, Favor, Against, or Neither) between comments and targets. Pretrained language models (PLMs) are widely used to mine the stance relation to improve the performance of stance detection…