Related papers: Curriculum Recommendations Using Transformer Base …

Cross-lingual topic models have been prevalent for cross-lingual text analysis by revealing aligned latent topics. However, most existing methods suffer from producing repetitive topics that hinder further analysis and performance decline…

Recently, matrix factorization-based recommendation methods have been criticized for the problem raised by the triangle inequality violation. Although several metric learning-based approaches have been proposed to overcome this issue,…

Diffusion Policies have become widely used in Imitation Learning, offering several appealing properties, such as generating multimodal and discontinuous behavior. As models are becoming larger to capture more complex capabilities, their…

Machine learning (ML) techniques are increasingly prevalent in education, from their use in predicting student dropout, to assisting in university admissions, and facilitating the rise of MOOCs. Given the rapid growth of these novel uses,…

In typical multimodal contrastive learning, such as CLIP, encoders produce one point in the latent representation space for each input. However, one-point representation has difficulty in capturing the relationship and the similarity…

Authorship has entangled style and content inside. Authors frequently write about the same topics in the same style, so when different authors write about the exact same topic the easiest way out to distinguish them is by understanding the…

Delivering high-quality content is crucial for effective reading comprehension and successful learning. Ensuring educational materials are interpreted as intended by their authors is a persistent challenge, especially with the added…

Curriculum learning provides a systematic approach to training. It refines training progressively, tailors training to task requirements, and improves generalization through exposure to diverse examples. We present a curriculum learning…

This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption. Specifically, for the first perspective, we identify that the dropout noise from negative…

This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to…

Pre-trained vision and language models such as CLIP have witnessed remarkable success in connecting images and texts with a primary focus on English texts. Despite recent efforts to extend CLIP to support other languages, disparities in…

Most curriculum learning methods require an approach to sort the data samples by difficulty, which is often cumbersome to perform. In this work, we propose a novel curriculum learning approach termed Learning Rate Curriculum (LeRaC), which…

Contrastive learning has gained popularity and pushes state-of-the-art performance across numerous large-scale benchmarks. In contrastive learning, the contrastive loss function plays a pivotal role in discerning similarities between…

Multilingual machine translation systems aim to make knowledge accessible across languages, yet learning effective cross-lingual representations remains challenging. These challenges are especially pronounced for low-resource languages,…

We consider the problem of teaching via demonstrations in sequential decision-making settings. In particular, we study how to design a personalized curriculum over demonstrations to speed up the learner's convergence. We provide a unified…

Continual learning is essential for adapting models to new tasks while retaining previously acquired knowledge. While existing approaches predominantly focus on uni-modal data, multi-modal learning offers substantial benefits by utilizing…

Modern sequential recommender systems commonly use transformer-based models for next-item prediction. While these models demonstrate a strong balance between efficiency and quality, integrating interleaving features - such as the query…

The prosperity of mobile and financial technologies has bred and expanded various kinds of financial products to a broader scope of people, which contributes to advocating financial inclusion. It has non-trivial social benefits of…

In self-supervised learning, one trains a model to solve a so-called pretext task on a dataset without the need for human annotation. The main objective, however, is to transfer this model to a target domain and task. Currently, the most…

The recent breakthrough of large language models (LLMs) in natural language processing has sparked exploration in recommendation systems, however, their limited domain-specific knowledge remains a critical bottleneck. Specifically, LLMs…