8 accepted papers
Zero-shot classifier expansion aims to adapt existing model to new, unseen classes. It utilizes class attributes or textual descriptions to learn a mapping from the semantic space to the classifier
Zero-shot classifier expansion aims to recognize unseen classes by learning a shared mechanism to map semantics of all classes to classifier weights without access to images. However, existing methods rely on a shared mapping, which is difficult to classify in scenarios containing a mixture of disti…
Learning instantaneous and time-lagged causal relationships from time-series data is essential for uncovering fine-grained, temporally-aware interactions. Although this problem has been formulated as a continuous optimization task amenable to modern machine learning methods, existing approaches larg…
Causal discovery aims to infer a Directed Acyclic Graph (DAG) from observational data to represent causal relationships among variables. Traditional combinatorial methods search DAG spaces to identify optimal structures, while recent advances in continuous optimization improve this search process. H…
Differentiable structure learning of causal directed acyclic graphs (DAGs) is an emerging field in causal discovery, leveraging powerful neural learners. However, the incorporation of ancestral constraints, essential for representing abstract prior causal knowledge, remains an open research challeng…
Zero-shot learning has shown significant potential for creating cost-effective and flexible systems to expand classifiers to new categories. However, existing methods still rely on manually created attributes designed by domain experts. Motivated by the widespread success of large language models (L
Learning the causality between variables, known as DAG structure learning, is critical yet challenging due to issues such as insufficient data and noise. While prior knowledge can improve the learning process and refine the DAG structure, incorporating prior knowledge is not without pitfalls. In par…
Differentiable structure learning is a novel line of causal discovery research that transforms the combinatorial optimization of structural models into a continuous optimization problem. However, the field has lacked feasible methods to integrate partial order constraints, a critical prior informati…