Generative Flow Networks (GFlowNets) have demonstrated significant performance improvements for generating diverse discrete objects $x$ given a reward function $R(x)$, indicating the utility of the object and trained independently from the GFlowNet by supervised learning to predict a desirable property $y$ given $x$. We hypothesize that this can lead to incompatibility between the inductive optimization biases in training $R$ and in training the GFlowNet, potentially leading to worse samples and slow adaptation to changes in the distribution. In this work, we build upon recent work on jointly learning energy-based models with GFlowNets and extend it to learn the joint over multiple variables, which we call Joint Energy-Based GFlowNets (JEBGFNs), such as peptide sequences and their antimicrobial activity. Joint learning of the energy-based model, used as a reward for the GFlowNet, can resolve the issues of incompatibility since both the reward function $R$ and the GFlowNet sampler are trained jointly. We find that this joint training or joint energy-based formulation leads to significant improvements in generating anti-microbial peptides. As the training sequences arose out of evolutionary or artificial selection for high antibiotic activity, there is presumably some structure in the distribution of sequences that reveals information about the antibiotic activity. This results in an advantage to modeling their joint generatively vs. pure discriminative modeling. We also evaluate JEBGFN in an active learning setting for discovering anti-microbial peptides.
DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Mila - Quebec AI Institute（Mila-魁北克人工智能研究所）；University Health Network（大学健康网络）；Université de Montréal（蒙特利尔大学）；Valence Labs（Valence实验室）
AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion
Bangladesh University of Engineering and Technology（孟加拉工程与技术大学）；University of California Riverside（加州大学河滨分校）；University of Southern California（南加州大学）；Princeton University（普林斯顿大学）
Inria（法国国家信息与自动化技术研究院）；PSL Research University（巴黎社会科学高等研究院）；CMAP（巴黎高等理工学院应用数学与计算科学实验室）；Ecole Polytechnique Palaiseau, France（法国巴黎高等理工学院Palaiseau分校）；Sakana AI Tokyo, Japan（日本东京Sakana AI公司）
Overcoming Dimensional Factorization Limits in Discrete Diffusion Models through Quantum Joint Distribution Learning
Faculty of Innovation Engineering, Macau University of Science and Technology（澳门科学技术大学创新工程学院）；Department of Electrical and Computer Engineering, New Jersey Institute of Technology（新泽西理工学院电气与计算机工程系）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；School of Electronic and Information Engineering, Foshan University（佛山大学电子与信息工程学院）；College of Mathematics and Informatics, South China Agricultural University（华南农业大学数学与信息学院）
A2D2: Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding
Department of Computer and Information Science, University of Pennsylvania（宾夕法尼亚大学计算机与信息科学系）；Department of Bioengineering, University of Pennsylvania（宾夕法尼亚大学生物工程系）；School of Mathematics, Georgia Institute of Technology（佐治亚理工学院数学学院）
Patient-specific Conditional Joint Models of Shape, Image Features and Clinical Indicators
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；German Centre for Neurodegenerative Diseases (DZNE)（德国神经退行性疾病中心）；Erasmus MC - University Medical Center Rotterdam（伊拉斯谟医学中心——鹿特丹大学医学中心）
From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training
California Institute of Technology（加州理工学院）；NVIDIA（英伟达）；Zuse Institute Berlin（柏林泽尼克研究所）；dida Datenschmiede GmbH（dida数据隐私公司）；Jagiellonian University（雅盖隆大学）；Mila, Université de Montréal（蒙特利尔大学机器学习研究所）；University of Edinburgh（爱丁堡大学）；CIFAR Fellow, Learning in Machines and Brains（CIFAR Fellow, 机器学习与大脑学习）
ScDiVa: Masked Discrete Diffusion for Joint Modeling of Single-Cell Identity and Expression
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China（中国人民大学人工智能学院）；School of Statistics, Renmin University of China, Beijing, China（中国人民大学统计学院）；CRE Life Institute, China（中国CRE生命科学研究院）；School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China（华中科技大学计算机科学与技术学院）；School of Mathematics, Jilin University, Changchun, China（吉林大学数学学院）；Beijing Academy of Artificial Intelligence,Beijing,China（北京人工智能研究院）
JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generation
Kognia Sports Intelligence（Kognia体育智能）；Visual Intelligence for Transportation, EPFL（交通视觉智能，EPFL）；Institut de Robòtica i Informàtica Industrial, CSIC-UPC（机器人与信息工业研究所，CSIC-UPC）
A General Deep Learning Framework for Wireless Resource Allocation under Discrete Constraints
Department of Electrical and Electronic Engineering, The University of Hong Kong（香港大学电子与电气工程系）；School of Computing and Information Technology, Great Bay University（大湾大学计算机与信息科技学院）；Department of Electrical and Computer Engineering, National University of Singapore（新加坡国立大学电子与计算机工程系）
Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
Department of Computer Science, School of Computing, Institute of Science Tokyo, Tokyo, Japan（东京科学研究所计算机科学系）；College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算机与数据科学学院）；PSL University, Paris, France（巴黎高等师范学院）
