10 citations · 26 across the 12 of their papers we have counts for
12 papers
ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts
Heng Zhao, Zilei Shao, Guy Van den Broeck +1
Mixture-of-Experts (MoE) models scale by activating only a small subset of experts per token. However, training such models remains challenging because top- routing is discrete…
Deep Generative Models with Hard Linear Equality Constraints
Ruoyan Li, Dipti Ranjan Sahu, Guy Van den Broeck +1
While deep generative models~(DGMs) have demonstrated remarkable success in capturing complex data distributions, they consistently fail to learn constraints that encode domain kno…
A Unified Approach to Count-Based Weakly-Supervised Learning
Vinay Shukla, Zhe Zeng, Kareem Ahmed +1
High-quality labels are often very scarce, whereas unlabeled data with inferred weak labels occurs more naturally. In many cases, these weak labels dictate the frequency of each re…
Probabilistically Rewired Message-Passing Neural Networks
Chendi Qian, Andrei Manolache, Kareem Ahmed +4
Message-passing graph neural networks (MPNNs) emerged as powerful tools for processing graph-structured input. However, they operate on a fixed input graph structure, ignoring pote…
Collapsed Inference for Bayesian Deep Learning
Zhe Zeng, Guy Van den Broeck
Bayesian neural networks (BNNs) provide a formalism to quantify and calibrate uncertainty in deep learning. Current inference approaches for BNNs often resort to few-sample estimat…
SIMPLE: A Gradient Estimator for -Subset Sampling
Kareem Ahmed, Zhe Zeng, Mathias Niepert +1
-subset sampling is ubiquitous in machine learning, enabling regularization and interpretability through sparsity. The challenge lies in rendering -subset sampling amenable t…
Autonomous Vehicles Drive into Shared Spaces: eHMI Design Concept Focusing on Vulnerable Road Users
Yang Li, Hao Cheng, Zhe Zeng +2
In comparison to conventional traffic designs, shared spaces promote a more pleasant urban environment with slower motorized movement, smoother traffic, and less congestion. In the…
Tractable Computation of Expected Kernels
Wenzhe Li, Zhe Zeng, Antonio Vergari +1
Computing the expectation of kernel functions is a ubiquitous task in machine learning, with applications from classical support vector machines to exploiting kernel embeddings of…
Scaling up Hybrid Probabilistic Inference with Logical and Arithmetic Constraints via Message Passing
Zhe Zeng, Paolo Morettin, Fanqi Yan +2
Weighted model integration (WMI) is a very appealing framework for probabilistic inference: it allows to express the complex dependencies of real-world problems where variables are…
Hybrid Probabilistic Inference with Logical Constraints: Tractability and Message Passing
Zhe Zeng, Fanqi Yan, Paolo Morettin +2
Weighted model integration (WMI) is a very appealing framework for probabilistic inference: it allows to express the complex dependencies of real-world hybrid scenarios where varia…
Efficient Search-Based Weighted Model Integration
Zhe Zeng, Guy Van den Broeck
Weighted model integration (WMI) extends Weighted model counting (WMC) to the integration of functions over mixed discrete-continuous domains. It has shown tremendous promise for s…
Stein Variational Message Passing for Continuous Graphical Models
Dilin Wang, Zhe Zeng, Qiang Liu
We propose a novel distributed inference algorithm for continuous graphical models, by extending Stein variational gradient descent (SVGD) to leverage the Markov dependency structu…