Dinghuai Zhang

Local Search GFlowNets

Minsu Kim

Sungsoo Ahn

Jinkyoo Park

Generative Flow Networks (GFlowNets) are amortized sampling methods that learn a distribution over discrete objects proportional to their re… (voir plus)wards. GFlowNets exhibit a remarkable ability to generate diverse samples, yet occasionally struggle to consistently produce samples with high rewards due to over-exploration on wide sample space. This paper proposes to train GFlowNets with local search, which focuses on exploiting high-rewarded sample space to resolve this issue. Our main idea is to explore the local neighborhood via backtracking and reconstruction guided by backward and forward policies, respectively. This allows biasing the samples toward high-reward solutions, which is not possible for a typical GFlowNet solution generation scheme, which uses the forward policy to generate the solution from scratch. Extensive experiments demonstrate a remarkable performance improvement in several biochemical tasks. Source code is available: https://github.com/dbsxodud-11/ls_gfn.

2023-10-04

ArXiv (prépublication)

Local Search GFlowNets

Minsu Kim

Sungsoo Ahn

Jinkyoo Park

2023-10-04

ArXiv (prépublication)

Local Search GFlowNets

Minsu Kim

Sungsoo Ahn

Jinkyoo Park

2023-10-04

ArXiv (prépublication)

Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets

Hanjun Dai

Ling Pan

Better Training of GFlowNets with Local Credit and Incomplete Trajectories

Ling Pan

Nikolay Malkin

Generative Flow Networks or GFlowNets are related to Monte-Carlo Markov chain methods (as they sample from a distribution specified by an en… (voir plus)ergy function), reinforcement learning (as they learn a policy to sample composed objects through a sequence of steps), generative models (as they learn to represent and sample from a distribution) and amortized variational methods (as they can be used to learn to approximate and sample from an otherwise intractable posterior, given a prior and a likelihood). They are trained to generate an object

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (publié)

openreview.net

Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets

Hanjun Dai

Ling Pan

Combinatorial optimization (CO) problems are often NP-hard and thus out of reach for exact algorithms, making them a tempting domain to appl… (voir plus)y machine learning methods. The highly structured constraints in these problems can hinder either optimization or sampling directly in the solution space. On the other hand, GFlowNets have recently emerged as a powerful machinery to efficiently sample from composite unnormalized densities sequentially and have the potential to amortize such solution-searching processes in CO, as well as generate diverse solution candidates. In this paper, we design Markov decision processes (MDPs) for different combinatorial problems and propose to train conditional GFlowNets to sample from the solution space. Efficient training techniques are also developed to benefit long-range credit assignment. Through extensive experiments on a variety of different CO tasks with synthetic and realistic data, we demonstrate that GFlowNet policies can efficiently find high-quality solutions. Our implementation is open-sourced at https://github.com/zdhNarsil/GFlowNet-CombOpt.

2023-05-26

ArXiv (prépublication)

Better Training of GFlowNets with Local Credit and Incomplete Trajectories

Ling Pan

Nikolay Malkin

2023-04-24

ICML.cc/2023/Conference (poster)

openreview.net

Stochastic Generative Flow Networks

Ling Pan

Moksh J. Jain

Longbo Huang

Generative Flow Networks (or GFlowNets for short) are a family of probabilistic agents that learn to sample complex combinatorial structures… (voir plus) through the lens of"inference as control". They have shown great potential in generating high-quality and diverse candidates from a given energy landscape. However, existing GFlowNets can be applied only to deterministic environments, and fail in more general tasks with stochastic dynamics, which can limit their applicability. To overcome this challenge, this paper introduces Stochastic GFlowNets, a new algorithm that extends GFlowNets to stochastic environments. By decomposing state transitions into two steps, Stochastic GFlowNets isolate environmental stochasticity and learn a dynamics model to capture it. Extensive experimental results demonstrate that Stochastic GFlowNets offer significant advantages over standard GFlowNets as well as MCMC- and RL-based approaches, on a variety of standard benchmarks with stochastic dynamics.

2023-02-19

ArXiv (prépublication)

Distributional GFlowNets with Quantile Flows

Ling Pan

Ricky T. Q. Chen

Aaron Courville

Generative Flow Networks (GFlowNets) are a new family of probabilistic samplers where an agent learns a stochastic policy for generating com… (voir plus)plex combinatorial structure through a series of decision-making steps. Despite being inspired from reinforcement learning, the current GFlowNet framework is relatively limited in its applicability and cannot handle stochasticity in the reward function. In this work, we adopt a distributional paradigm for GFlowNets, turning each flow function into a distribution, thus providing more informative learning signals during training. By parameterizing each edge flow through their quantile functions, our proposed \textit{quantile matching} GFlowNet learning algorithm is able to learn a risk-sensitive policy, an essential component for handling scenarios with risk uncertainty. Moreover, we find that the distributional approach can achieve substantial improvement on existing benchmarks compared to prior methods due to our enhanced training algorithm, even in settings with deterministic rewards.

2023-02-11

ArXiv (prépublication)

Better Training of GFlowNets with Local Credit and Incomplete Trajectories

Ling Pan

Nikolay Malkin

Generative Flow Networks or GFlowNets are related to Monte-Carlo Markov chain methods (as they sample from a distribution specified by an en… (voir plus)ergy function), reinforcement learning (as they learn a policy to sample composed objects through a sequence of steps), generative models (as they learn to represent and sample from a distribution) and amortized variational methods (as they can be used to learn to approximate and sample from an otherwise intractable posterior, given a prior and a likelihood). They are trained to generate an object

2023-02-03

ArXiv (prépublication)

Generative Augmented Flow Networks

Ling Pan

Aaron Courville

Longbo Huang

The Generative Flow Network is a probabilistic framework where an agent learns a stochastic policy for object generation, such that the prob… (voir plus)ability of generating an object is proportional to a given reward function. Its effectiveness has been shown in discovering high-quality and diverse solutions, compared to reward-maximizing reinforcement learning-based methods. Nonetheless, GFlowNets only learn from rewards of the terminal states, which can limit its applicability. Indeed, intermediate rewards play a critical role in learning, for example from intrinsic motivation to provide intermediate feedback even in particularly challenging sparse reward tasks. Inspired by this, we propose Generative Augmented Flow Networks (GAFlowNets), a novel learning framework to incorporate intermediate rewards into GFlowNets. We specify intermediate rewards by intrinsic motivation to tackle the exploration problem in sparse reward environments. GAFlowNets can leverage edge-based and state-based intrinsic rewards in a joint way to improve exploration. Based on extensive experiments on the GridWorld task, we demonstrate the effectiveness and efficiency of GAFlowNet in terms of convergence, performance, and diversity of solutions. We further show that GAFlowNet is scalable to a more complex and large-scale molecule generation domain, where it achieves consistent and significant performance improvement.

2023-02-01

ICLR.cc/2023/Conference (notable)