Related papers: Seeded Poisson Factorization: leveraging domain kn…

Test-time personalization in federated learning enables models at clients to adjust online to local domain shifts, enhancing robustness and personalization in deployment. Yet, existing federated learning work largely overlooks the security…

We introduce Segmentation by Factorization (F-SEG), an unsupervised segmentation method for pathology that generates segmentation masks from pre-trained deep learning models. F-SEG allows the use of pre-trained deep neural networks,…

Topic detection is a complex process and depends on language because it somehow needs to analyze text. There have been few studies on topic detection in Persian, and the existing algorithms are not remarkable. Therefore, we aimed to study…

The rapid development of multimedia has provided a large amount of data with different distributions for visual tasks, forming different domains. Federated Learning (FL) can efficiently use this diverse data distributed on different client…

Practitioners from many disciplines (e.g., political science) use expert-crafted taxonomies to make sense of large, unlabeled corpora. In this work, we study Seeded Hierarchical Clustering (SHC): the task of automatically fitting unlabeled…

Data sparsity is an inherent challenge in the recommender systems, where most of the data is collected from the implicit feedbacks of users. This causes two difficulties in designing effective algorithms: first, the majority of users only…

We propose and evaluate an automated pipeline for discovering significant topics from legal decision texts by passing features synthesized with topic models through penalised regressions and post-selection significance tests. The method…

Recently, considerable research effort has been devoted to developing deep architectures for topic models to learn topic structures. Although several deep models have been proposed to learn better topic proportions of documents, how to…

Topic evolution modeling has been researched for a long time and has gained considerable interest. A state-of-the-art method has been recently using word modeling algorithms in combination with community detection mechanisms to achieve…

There is a growing interest in subject-specific predictions using deep neural networks (DNNs) because real-world data often exhibit correlations, which has been typically overlooked in traditional DNN frameworks. In this paper, we propose a…

Semantic matching of natural language sentences or identifying the relationship between two sentences is a core research problem underlying many natural language tasks. Depending on whether training data is available, prior research has…

Topic modeling is a key method in text analysis, but existing approaches fail to efficiently scale to large datasets or are limited by assuming one topic per document. Overcoming these limitations, we introduce Semantic Component Analysis…

We tackle the task of Term Set Expansion (TSE): given a small seed set of example terms from a semantic class, finding more members of that class. The task is of great practical utility, and also of theoretical utility as it requires…

Semi-supervised learning (SSL) essentially pursues class boundary exploration with less dependence on human annotations. Although typical attempts focus on ameliorating the inevitable error-prone pseudo-labeling, we think differently and…

Stochastic Discount Factor (SDF) models provide a unified framework for asset pricing and risk assessment, yet traditional formulations struggle to incorporate unstructured textual information. We introduce NewsNet-SDF, a novel deep…

Network-based procedures for topic detection in huge text collections offer an intuitive alternative to probabilistic topic models. We present in detail a method that is especially designed with the requirements of domain experts in mind.…

Recently, topic modeling has been widely used to discover the abstract topics in text corpora. Most of the existing topic models are based on the assumption of three-layer hierarchical Bayesian structure, i.e. each document is modeled as a…

In the rapidly evolving realm of machine learning, algorithm effectiveness often faces limitations due to data quality and availability. Traditional approaches grapple with data sharing due to legal and privacy concerns. The federated…

Concept Factorization (CF), as a novel paradigm of representation learning, has demonstrated superior performance in multi-view clustering tasks. It overcomes limitations such as the non-negativity constraint imposed by traditional matrix…

Recent advances in pre-trained language modeling have facilitated significant progress across various natural language processing (NLP) tasks. Word masking during model training constitutes a pivotal component of language modeling in…