STERLING: Synergistic Representation Learning on Bipartite Graphs
A fundamental challenge of bipartite graph representation learning is how to extract informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to address this challenge. Most...
View ArticleOnline Reinforcement Learning in Non-Stationary Context-Driven Environments
We study online reinforcement learning (RL) in non-stationary environments, where a time-varying exogenous context process affects the environment dynamics. Online RL is challenging in such...
View ArticleA Survey of Deep Learning: From Activations to Transformers
Deep learning has made tremendous progress in the last decade. A key success factor is the large amount of architectures, layers, objectives, and optimization techniques. They include a myriad of...
View ArticleRethinking the Expressive Power of GNNs via Graph Biconnectivity
Designing expressive Graph Neural Networks (GNNs) is a central topic in learning graph-structured data. While numerous approaches have been proposed to improve GNNs in terms of the Weisfeiler-Lehman...
View ArticleEfficient Preference-Based Reinforcement Learning Using Learned Dynamics Models
Preference-based reinforcement learning (PbRL) can enable robots to learn to perform tasks based on an individual's preferences without requiring a hand-crafted reward function. However, existing...
View ArticleFlow: Per-Instance Personalized Federated Learning Through Dynamic Routing
Personalization in Federated Learning (FL) aims to modify a collaboratively trained global model according to each client. Current approaches to personalization in FL are at a coarse granularity, i.e....
View ArticleWhen is Momentum Extragradient Optimal? A Polynomial-Based Analysis
The extragradient method has gained popularity due to its robust convergence properties for differentiable games. Unlike single-objective optimization, game dynamics involve complex interactions...
View ArticleFederated Causal Discovery From Interventions
Causal discovery serves a pivotal role in mitigating model uncertainty through recovering the underlying causal mechanisms among variables. In many practical domains, such as healthcare, access to the...
View ArticleDynamic Latent Separation for Deep Learning
A core problem in machine learning is to learn expressive latent variables for model prediction on complex data that involves multiple sub-components in a flexible and interpretable fashion. Here, we...
View ArticleGBSVM: Granular-ball Support Vector Machine
GBSVM (Granular-ball Support Vector Machine) is a significant attempt to construct a classifier using the coarse-to-fine granularity of a granular-ball as input, rather than a single data point. It is...
View ArticleNeuralVDB: High-resolution Sparse Volume Representation using Hierarchical...
We introduce NeuralVDB, which improves on an existing industry standard for efficient storage of sparse volumetric data, denoted VDB [Museth 2013], by leveraging recent advancements in machine...
View ArticleCompositional Q-learning for electrolyte repletion with imbalanced patient...
Reinforcement learning (RL) is an effective framework for solving sequential decision-making tasks. However, applying RL methods in medical care settings is challenging in part due to heterogeneity in...
View ArticleComputationally Efficient High-Dimensional Bayesian Optimization via Variable...
Bayesian Optimization (BO) is a method for globally optimizing black-box functions. While BO has been successfully applied to many scenarios, developing effective BO algorithms that scale to functions...
View ArticleA systematic investigation of learnability from single child linguistic input
Language models (LMs) have demonstrated remarkable proficiency in generating linguistically coherent text, sparking discussions about their relevance to understanding human language learnability....
View ArticleLabel-Efficient Model Selection for Text Generation
Model selection for a given target task can be costly, as it may entail extensive annotation of the quality of outputs of different models. We introduce DiffUse, an efficient method to make an informed...
View ArticleMAIDCRL: Semi-centralized Multi-Agent Influence Dense-CNN Reinforcement Learning
Distributed decision-making in multi-agent systems presents difficult challenges for interactive behavior learning in both cooperative and competitive systems. To mitigate this complexity, MAIDRL...
View ArticleUsing Graph Theory for Improving Machine Learning-based Detection of Cyber...
Early detection of network intrusions and cyber threats is one of the main pillars of cybersecurity. One of the most effective approaches for this purpose is to analyze network traffic with the help of...
View ArticlePIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs
Vision language models (VLMs) have shown impressive capabilities across a variety of tasks, from logical reasoning to visual understanding. This opens the door to richer interaction with the world, for...
View ArticlePoisonedRAG: Knowledge Poisoning Attacks to Retrieval-Augmented Generation of...
Large language models (LLMs) have achieved remarkable success due to their exceptional generative capabilities. Despite their success, they also have inherent limitations such as a lack of up-to-date...
View ArticlePrismatic VLMs: Investigating the Design Space of Visually-Conditioned...
Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning; adoption that has fueled a wealth of new...
View Article