Related papers: Seeded Poisson Factorization: leveraging domain kn…

Manipulation of local training data and local updates, i.e., the poisoning attack, is the main threat arising from the collaborative nature of the federated learning (FL) paradigm. Most existing poisoning attacks aim to manipulate local…

We introduce the probabilistic sequential matrix factorization (PSMF) method for factorizing time-varying and non-stationary datasets consisting of high-dimensional time-series. In particular, we consider nonlinear Gaussian state-space…

Various informative factors mixed in speech signals, leading to great difficulty when decoding any of the factors. An intuitive idea is to factorize each speech frame into individual informative factors, though it turns out to be highly…

Pixel-level vision tasks, such as semantic segmentation, require extensive and high-quality annotated data, which is costly to obtain. Semi-supervised semantic segmentation (SSSS) has emerged as a solution to alleviate the labeling burden…

While federated learning is promising for privacy-preserving collaborative learning without revealing local data, it remains vulnerable to white-box attacks and struggles to adapt to heterogeneous clients. Federated distillation (FD), built…

Legacy procedures for topic modelling have generally suffered problems of overfitting and a weakness towards reconstructing sparse topic structures. With motivation from a consumer-generated corpora, this paper proposes semiparametric topic…

In this paper, we investigate the unsupervised deep representation learning issue and technically propose a novel framework called Deep Self-representative Concept Factorization Network (DSCF-Net), for clustering deep features. To improve…

Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we propose a novel approach to…

In this paper we study predictive pattern mining problems where the goal is to construct a predictive model based on a subset of predictive patterns in the database. Our main contribution is to introduce a novel method called safe pattern…

Knowledge tracing is a sequence prediction problem where the goal is to predict the outcomes of students over questions as they are interacting with a learning platform. By tracking the evolution of the knowledge of some student, one can…

Although masked language models are highly performant and widely adopted by NLP practitioners, they can not be easily used for autoregressive language modelling (next word prediction and sequence probability estimation). We present an…

The behavior of many Bayesian models used in machine learning critically depends on the choice of prior distributions, controlled by some hyperparameters that are typically selected by Bayesian optimization or cross-validation. This…

Poisson non-negative matrix factorization (NMF) is a widely used method to find interpretable "parts-based" decompositions of count data. While many variants of Poisson NMF exist, existing methods assume that the "parts" in the…

Finding an optimal word representation algorithm is particularly important in terms of domain specific data, as the same word can have different meanings and hence, different representations depending on the domain and context. While…

Topic modeling is pivotal in discerning hidden semantic structures within texts, thereby generating meaningful descriptive keywords. While innovative techniques like BERTopic and Top2Vec have recently emerged in the forefront, they manifest…

Knowledge acquisition and exchange are generally crucial yet costly for both businesses and individuals, especially when the knowledge concerns various areas. Question Answering Communities offer an opportunity for sharing knowledge at a…

Supervised matrix factorization (SMF) is a classical machine learning method that simultaneously seeks feature extraction and classification tasks, which are not necessarily a priori aligned objectives. Our goal is to use SMF to learn…

Topic modeling is widely used for uncovering thematic structures within text corpora, yet traditional models often struggle with specificity and coherence in domain-focused applications. Guided approaches, such as SeededLDA and CorEx,…

Pathology foundation models (PFMs) have rapidly advanced and are becoming a common backbone for downstream clinical tasks, offering strong transferability across tissues and institutions. However, for dense prediction (e.g., segmentation),…

Semi-Non-negative Matrix Factorization is a technique that learns a low-dimensional representation of a dataset that lends itself to a clustering interpretation. It is possible that the mapping between this new representation and our…