Related papers: A Unifying Framework for Unsupervised Concept Extr…

In information retrieval, a fundamental goal is to transform a document into concepts that are representative of its content. The term "representative" is in itself challenging to define, and various tasks require different granularities of…

Diagnosing hematological malignancies requires identification and classification of white blood cells in peripheral blood smears. Domain shifts caused by different lab procedures, staining, illumination, and microscope settings hamper the…

In recent years, machine learning methods have been used to assist scientists in scientific research. Human scientific theories are based on a series of concepts. How machine learns the concepts from experimental data will be an important…

We present a conceptual framework that unifies a variety of evaluation metrics for different structured prediction tasks (e.g. event and relation extraction, syntactic and semantic parsing). Our framework requires representing the outputs…

Experimental evidence indicates that simple models outperform complex deep networks on many unsupervised similarity tasks. We provide a simple yet rigorous explanation for this behaviour by introducing the concept of an optimal…

We introduce Sparse Concept Anchoring, a method that biases latent space to position a targeted subset of concepts while allowing others to self-organize, using only minimal supervision (labels for <0.1% of examples per anchored concept).…

Our work addresses the problem of unsupervised Aspect Category Detection using a small set of seed words. Recent works have focused on learning embedding spaces for seed words and sentences to establish similarities between sentences and…

Shortcut learning, i.e., a model's reliance on undesired features not directly relevant to the task, is a major challenge that severely limits the applications of machine learning algorithms, particularly when deploying them to assist in…

Diffusion models, while powerful, can inadvertently generate harmful or undesirable content, raising significant ethical and safety concerns. Recent machine unlearning approaches offer potential solutions but often lack transparency, making…

We propose split-brain autoencoders, a straightforward modification of the traditional autoencoder architecture, for unsupervised representation learning. The method adds a split to the network, resulting in two disjoint sub-networks. Each…

Our work focuses on unsupervised and generative methods that address the following goals: (a) learning unsupervised generative representations that discover latent factors controlling image semantic attributes, (b) studying how this ability…

State-of-the-art approaches for image captioning require supervised training data consisting of captions with paired image data. These methods are typically unable to use unsupervised data such as textual data with no corresponding images,…

Single-cell RNA-seq foundation models achieve strong performance on downstream tasks but remain black boxes, limiting their utility for biological discovery. Recent work has shown that sparse dictionary learning can extract concepts from…

To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive…

A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning…

Recent neural sequence-to-sequence models with a copy mechanism have achieved remarkable progress in various text generation tasks. These models addressed out-of-vocabulary problems and facilitated the generation of rare words. However, the…

With the increasing demands for accountability, interpretability is becoming an essential capability for real-world AI applications. However, most methods utilize post-hoc approaches rather than training the interpretable model. In this…

Visual text recognition is undoubtedly one of the most extensively researched topics in computer vision. Great progress have been made to date, with the latest models starting to focus on the more practical "in-the-wild" setting. However, a…

Deep generative models, while revolutionizing fields like image and text generation, largely operate as opaque ``black boxes'', hindering human understanding, control, and alignment. While methods like sparse autoencoders (SAEs) show…

Feature extraction is an efficient approach for alleviating the issue of dimensionality in high-dimensional data. As a popular self-supervised learning method, contrastive learning has recently garnered considerable attention. In this…