相关论文: Exploring Transferable Homogeneous Groups for Comp…

Predictive models trained on observational data often fail to generalise to the distributions they encounter when deployed, especially when the training data is a product of the system being optimised. Recommender systems are a canonical…

Molecular property prediction refers to the task of labeling molecules with some biochemical properties, playing a pivotal role in the drug discovery and design process. Recently, with the advancement of machine learning, deep…

This paper addresses intervention-based causal representation learning (CRL) under a general nonparametric latent causal model and an unknown transformation that maps the latent variables to the observed variables. Linear and general…

The goal of open-world compositional zero-shot learning (OW-CZSL) is to recognize compositions of state and objects in images, given only a subset of them during training and no prior on the unseen compositions. In this setting, models…

Temporal Knowledge Graph (TKG) representation learning embeds entities and event types into a continuous low-dimensional vector space by integrating the temporal information, which is essential for downstream tasks, e.g., event prediction…

This paper focuses on causal representation learning (CRL) under a general nonparametric latent causal model and a general transformation model that maps the latent data to the observational data. It establishes identifiability and…

We develop a novel compositional generative model for zero- and few-shot learning to recognize fine-grained classes with a few or no training samples. Our key observation is that generating holistic features for fine-grained classes fails…

Fine-grained visual categorization is to recognize hundreds of subcategories belonging to the same basic-level category, which is a highly challenging task due to the quite subtle and local visual distinctions among similar subcategories.…

Goal-Conditioned Reinforcement Learning (GCRL) enables agents to autonomously acquire diverse behaviors, but faces major challenges in visual environments due to high-dimensional, semantically sparse observations. In the online setting,…

Heterogeneity in federated learning (FL) is a critical and challenging aspect that significantly impacts model performance and convergence. In this paper, we propose a novel framework by formulating heterogeneous FL as a hierarchical…

Due to the challenge posed by multi-source and heterogeneous data collected from diverse environments, causal relationships among features can exhibit variations influenced by different time spans, regions, or strategies. This diversity…

Humans recognize objects after observing only a few examples, a remarkable capability enabled by their inherent language understanding of the real-world environment. Developing verbalized and interpretable representation can significantly…

This paper presents a novel approach that leverages domain variability to learn representations that are conditionally invariant to unwanted variability or distractors. Our approach identifies both spurious and invariant latent features…

Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a stream of high-dimensional, unstructured, and unlabeled observations is a tricky…

Compositional Zero-Shot Learning (CZSL) has emerged as an essential paradigm in machine learning, aiming to overcome the constraints of traditional zero-shot learning by incorporating compositional thinking into its methodology.…

Though graph representation learning (GRL) has made significant progress, it is still a challenge to extract and embed the rich topological structure and feature information in an adequate way. Most existing methods focus on local structure…

Data-free knowledge distillation transfers knowledge by recovering training data from a pre-trained model. Despite the recent success of seeking global data diversity, the diversity within each class and the similarity among different…

Holographic Reduced Representations (HRR) are a method for performing symbolic AI on top of real-valued vectors by associating each vector with an abstract concept, and providing mathematical operations to manipulate vectors as if they were…

Compositional Zero-Shot Learning (CZSL) aims to recognize subtle differences in meaning or the combination of states and objects through the use of known and unknown concepts during training. Existing methods either focused on prompt…

Zero-shot learning (ZSL) addresses the unseen class recognition problem by leveraging semantic information to transfer knowledge from seen classes to unseen classes. Generative models synthesize the unseen visual features and convert ZSL…