Generative Flow Networks (GFlowNets) are amortized samplers that learn stochastic policies to sequentially generate compositional objects from a given unnormalized reward distribution. They can generate diverse sets of high-reward objects, which is an important consideration in scientific discovery tasks. However, as they are typically trained from a given extrinsic reward function, it remains an important open challenge about how to leverage the power of pre-training and train GFlowNets in an unsupervised fashion for efficient adaptation to downstream tasks. Inspired by recent successes of unsupervised pre-training in various domains, we introduce a novel approach for reward-free pre-training of GFlowNets. By framing the training as a self-supervised problem, we propose an outcome-conditioned GFlowNet (OC-GFN) that learns to explore the candidate space. Specifically, OC-GFN learns to reach any targeted outcomes, akin to goal-conditioned policies in reinforcement learning. We show that the pre-trained OC-GFN model can allow for a direct extraction of a policy capable of sampling from any new reward functions in downstream tasks. Nonetheless, adapting OC-GFN on a downstream task-specific reward involves an intractable marginalization over possible outcomes. We propose a novel way to approximate this marginalization by learning an amortized predictor enabling efficient fine-tuning. Extensive experimental results validate the efficacy of our approach, demonstrating the effectiveness of pre-training the OC-GFN, and its ability to swiftly adapt to downstream tasks and discover modes more efficiently. This work may serve as a foundation for further exploration of pre-training strategies in the context of GFlowNets.
Constrained Flow Optimization via Sequential Fine Tuning for Molecular Design
Department of Computer Science, ETH Zurich（苏黎世联邦理工学院计算机科学系）；Institute of Chemical and Bioengineering, Department of Chemistry and Applied Biosciences, ETH Zurich（苏黎世联邦理工学院化学与生物工程研究所）；ETH AI Center（苏黎世联邦理工学院人工智能中心）
Beijing National Laboratory for Condensed Matter Physics（北京凝聚态物理国家实验室）；School of Physical Sciences, University of Chinese Academy of Sciences, Beijing 100190, China（中国科学院大学物理科学学院）；Songshan Lake Materials Laboratory, Dongguan, Guangdong 523808, China（松山湖材料实验室）
FRAGMENTA: Efficient End-to-end Fragmentation-based Generative Model with Agentic Tuning for Drug Lead Optimization in Small Data Regime
Department of Computer Science and Engineering（计算机科学与工程系）；University of Colorado Denver（科罗拉多大学丹佛分校）；Skaggs School of Pharmacy（斯卡格斯药学院）；University of Colorado Anschutz Medical Campus（科罗拉多大学安舒茨医疗分校）
Georgia Institute of Technology（佐治亚理工学院）；SIEMENS Corporate Technology（西门子企业技术）
To efficiently run DNNs on the edge/cloud, many new DNN inference accelerators are being designed and deployed frequently. To enhance the resource efficiency of DNNs, model quantization is a widely-used approach. However, different accelerator/HW has different resources leading to the need for specialized quantization strategy of each HW. Moreover, using the same quantization for every layer may be sub-optimal, increasing the designspace of possible quantization choices. This makes manual-tuning infeasible. Recent work in automatically determining quantization for each layer is driven by optim…
The paper focuses on the a posteriori tuning of a generative model in order to favor the generation of good instances in the sense of some external differentiable criterion. The proposed approach, called Boltzmann Tuning of Generative Models (BTGM), applies to a wide range of applications. It covers conditional generative modelling as a particular case, and offers an affordable alternative to rejection sampling. The contribution of the paper is twofold. Firstly, the objective is formalized and tackled as a well-posed optimization problem; a practical methodology is proposed to choose among the…
Geometry Preserving Loss Functions Promote Improved Adaptation of Blackbox Generative Model
Geometric Media Lab（几何媒体实验室）；Arizona State University（亚利桑那州立大学）；Department of Statistics（统计学系）；Florida State University（佛罗里达州立大学）；Department of Computer Science and Engineering（计算机科学与工程系）；Seoul National University of Science and Technology（首尔科学技术大学）；Amazon（亚马逊）；Apple Inc.（苹果公司）
GenFT: A Generative Parameter-Efficient Fine-Tuning Method for Pretrained Foundation Models
Department of Mathematics, Hong Kong Baptist University, Hong Kong, China（香港 Baptist 大学数学系，香港，中国）；Department of Computer Science, Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学（深圳）计算机科学系，中国）
Tuning curves characterizing the response selectivities of biological neurons often exhibit large degrees of irregularity and diversity across neurons. Theoretical network models that feature heterogeneous cell populations or random connectivity also give rise to diverse tuning curves. However, a general framework for fitting such models to experimentally measured tuning curves is lacking. We address this problem by proposing to view mechanistic network models as generative models whose parameters can be optimized to fit the distribution of experimentally measured tuning curves. A major obstac…
Unsupervised Generative Feature Transformation via Graph Contrastive Pre-training and Multi-objective Fine-tuning
Arizona State University（亚利桑那州立大学）；University of Kansas（堪萨斯大学）；Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心）；IBM T. J. Watson Research Center（IBM T. J. 沃森研究中心）
GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning
SKLCCSE, School of Computer Science and Engineering, Beihang University（北京航空航天大学信息与电子技术学院）；Key Lab of Education Blockchain and Intelligent Technology, Guangxi Normal University（广西师范大学教育区块链与智能技术重点实验室）；School of Computing, National University of Singapore（新加坡国立大学计算机学院）；Department of Computer Science, University of Illinois, Chicago（伊利诺伊大学芝加哥分校计算机科学系）
Speech representations learned from Self-supervised learning (SSL) models can benefit various speech processing tasks. However, utilizing SSL representations usually requires fine-tuning the pre-trained models or designing task-specific downstream models and loss functions, causing much memory usage and human labor. Recently, prompting in Natural Language Processing (NLP) has been found to be an efficient technique to leverage pre-trained language models (LMs). Specifically, prompt tuning optimizes a limited number of task-specific parameters with a fixed pre-trained model; as a result, only a…
Efficient Fine-Tuning Methods for Portuguese Question Answering: A Comparative Study of PEFT on BERTimbau and Exploratory Evaluation of Generative LLMs
Institute of Science and Technology（科学技术研究院）；Federal University of São Paulo (UNIFESP)（圣保罗联邦大学）
Systematic trading strategies are algorithmic procedures that allocate assets aiming to optimize a certain performance criterion. To obtain an edge in a highly competitive environment, the analyst needs to proper fine-tune its strategy, or discover how to combine weak signals in novel alpha creating manners. Both aspects, namely fine-tuning and combination, have been extensively researched using several methods, but emerging techniques such as Generative Adversarial Networks can have an impact into such aspects. Therefore, our work proposes the use of Conditional Generative Adversarial Network…
For a data holder, such as a hospital or a government entity, who has a privately held collection of personal data, in which the revealing and/or processing of the personal identifiable data is restricted and prohibited by law. Then, "how can we ensure the data holder does conceal the identity of each individual in the imagery of personal data while still preserving certain useful aspects of the data after de-identification?" becomes a challenge issue. In this work, we propose an approach towards high-resolution facial image de-identification, called k-Same-Siamese-GAN, which leverages the k-S…
Physics-Constrained Fine-Tuning of Flow-Matching Models for Generation and Inverse Problems
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Department of Computer Science, University of Kaiserslautern–Landau (RPTU)（凯泽斯劳滕-兰道大学计算机科学系）；Department of Mathematics, Imperial College London（伦敦帝国理工学院数学系）
Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）
The Generative Adversarial Network (GAN) is a powerful and flexible tool that can generate high-fidelity synthesized data by learning. It has seen many applications in simulating events in High Energy Physics (HEP), including simulating detector responses and physics events. However, training GANs is notoriously hard and optimizing their hyperparameters even more so. It normally requires many trial-and-error training attempts to force a stable training and reach a reasonable fidelity. Significant tuning work has to be done to achieve the accuracy required by physics analyses. This work uses th…
Automated Tuning for Diffusion Inverse Problem Solvers without Generative Prior Retraining
Department of Electrical \& Computer Engineering, University of Minnesota, MN, USA；Center for Magnetic Resonance Research, University of Minnesota, MN, USA
Athens University of Economics and Business（雅典经济与商业大学）
Food is essential to human survival. So much so that we have developed different recipes to suit our taste needs. In this work, we propose a novel way of creating new, fine-dining recipes from scratch using Transformers, specifically auto-regressive language models. Given a small dataset of food recipes, we try to train models to identify cooking techniques, propose novel recipes, and test the power of fine-tuning with minimal data.
CSI-GPT: Integrating Generative Pre-Trained Transformer with Federated-Tuning to Acquire Downlink Massive MIMO Channels
School of Information and Electronics, Beijing Institute of Technology（北京理工大学信息与电子学院）；King Abdulaziz University（阿卜杜勒阿齐兹国王大学）；School of Electronics and Computer Science, University of Southampton（南安普顿大学电子与计算机科学学院）；Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）
