Author name cluster

Zarif Ikram

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

TMLR Journal 2025 Journal Article

Evolution guided generative flow networks

Zarif Ikram
Ling Pan
Dianbo Liu

Generative Flow Networks (GFlowNets) are a family of probabilistic generative models recently invented that learn to sample compositional objects proportional to their rewards. One big challenge of GFlowNets is training them effectively when dealing with long time horizons and sparse rewards. To address this, we propose Evolution guided generative flow networks (EGFN), a simple but powerful augmentation to the GFlowNets training using Evolutionary algorithms (EA). Our method can work on top of any GFlowNets training objective, by training a set of agent parameters using EA, storing the resulting trajectories in the prioritized replay buffer, and training the GFlowNets agent using the stored trajectories. We present a thorough investigation over a wide range of toy and real-world benchmark tasks showing the effectiveness of our method in handling long trajectories and sparse rewards. We release the code at http://github.com/zarifikram/egfn.

PDF Details

TMLR Journal 2024 Journal Article

Gradient-guided discrete walk-jump sampling for biological sequence generation

Zarif Ikram
Dianbo Liu
M Saifur Rahman

In this work, we propose gradient-guided discrete walk-jump sampling (gg-dWJS), a novel discrete sequence generation method for biological sequence optimization. Leveraging gradient guidance in the noisy manifold, we sample from the smoothed data manifold by applying discretized Markov chain Monte Carlo (MCMC) using a denoising model with the gradient-guidance from a discriminative model. This is followed by jumping to the discrete data manifold using a conditional one-step denoising. We showcase our method in two different modalities: discrete image and biological sequence involving antibody and peptide sequence generation tasks in the single objective and multi-objective setting. Through evaluation on these tasks, we show that our method generates high-quality samples that are well-optimized for specific tasks.

PDF Details