paper-with-me

홈 › Papers

Terminating Differentiable Tree Experts

2024-07-02 · Jonathan Thomm, Michael Hersche, Giacomo Camposampiero, Aleksandar Terzić, Bernhard Schölkopf, Abbas Rahimi

We advance the recently proposed neuro-symbolic Differentiable Tree Machine, which learns tree operations using a combination of transformers and Tensor Product Representations. We investigate the architecture and propose two key components. We first remove a series of different transformer layers that are used in every step by introducing a mixture of experts. This results in a Differentiable Tree Experts model with a constant number of parameters for any arbitrary number of steps in the computation, compared to the previous method in the Differentiable Tree Machine with a linear growth. Given this flexibility in the number of steps, we additionally propose a new termination algorithm to provide the model the power to choose how many steps to make automatically. The resulting Terminating Differentiable Tree Experts model sluggishly learns to predict the number of steps without an oracle. It can do so while maintaining the learning capabilities of the model, converging to the optimal amount of steps.

📄 PDF Abstract BibTeX arXiv:2407.02060

Code (0)

등록된 구현이 없습니다.

Tasks

Mixture-of-Experts

Similar Papers 제목 키워드 기반

Densities of Almost Surely Terminating Probabilistic Programs are Differentiable Almost Everywhere

2020-04-08 · Carol Mak, C. -H. Luke Ong, Hugo Paquet, Dominik Wagner

We study the differential properties of higher-order statistical probabilistic programs with recursion and conditioning. Our starting point is an open problem posed by Hongseok Yang: what class of statistical probabilist…

Differentiable Scaffolding Tree for Molecule Optimization

2021-09-29 · ICLR 2022 4 · Tianfan Fu, Wenhao Gao, Cao Xiao, Jacob Yasonik 외

The structural design of functional molecules, also called molecular optimization, is an essential chemical science and engineering task with important applications, such as drug discovery. Deep generative models and com…

Combinatorial OptimizationDrug DiscoveryGraph Neural Network

Differentiable Scaffolding Tree for Molecular Optimization

2021-09-22 · Tianfan Fu, Wenhao Gao, Cao Xiao, Jacob Yasonik 외

The structural design of functional molecules, also called molecular optimization, is an essential chemical science and engineering task with important applications, such as drug discovery. Deep generative models and com…

Combinatorial OptimizationDrug DiscoveryGraph Neural Network

MoET: Interpretable and Verifiable Reinforcement Learning via Mixture of Expert Trees

2019-09-25 · Marko Vasic, Andrija Petrovic, Kaiyuan Wang, Mladen Nikolic 외

Deep Reinforcement Learning (DRL) has led to many recent breakthroughs on complex control tasks, such as defeating the best human player in the game of Go. However, decisions made by the DRL agent are not explainable, hi…

Deep Reinforcement LearningGame of GoImitation LearningMixture-of-Experts+3

MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning

2019-06-16 · Marko Vasic, Andrija Petrovic, Kaiyuan Wang, Mladen Nikolic 외

Rapid advancements in deep learning have led to many recent breakthroughs. While deep learning models achieve superior performance, often statistically better than humans, their adoption into safety-critical settings, su…

Game of GoImitation LearningMixture-of-ExpertsOpenAI Gym+4