Self-supervised training methods for transformers have demonstrated remarkable performance across various domains. Previous transformer-based models, such as masked autoencoders (MAE), typically utilize a single normalization layer for both the [CLS] symbol and the tokens. We propose in this paper a simple modification that employs separate normalization layers for the tokens and the [CLS] symbol to better capture their distinct characteristics and enhance downstream task performance. Our method aims to alleviate the potential negative effects of using the same normalization statistics for both token types, which may not be optimally aligned with their individual roles. We empirically show that by utilizing a separate normalization layer, the [CLS] embeddings can better encode the global contextual information and are distributed more uniformly in its anisotropic space. When replacing the conventional normalization layer with the two separate layers, we observe an average 2.7% performance improvement over the image, natural language, and graph domains.
more »
« less
Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher.
Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?
Some links on this page may take you to non-federal websites. Their policies may differ from this site.
-
-
Self-supervised training methods for transformers have demonstrated remarkable performance across various domains. Previous transformer-based models, such as masked autoencoders (MAE), typically utilize a single normalization layer for both the [CLS] symbol and the tokens. We propose in this paper a simple modification that employs separate normalization layers for the tokens and the [CLS] symbol to better capture their distinct characteristics and enhance downstream task performance. Our method aims to alleviate the potential negative effects of using the same normalization statistics for both token types, which may not be optimally aligned with their individual roles. We empirically show that by utilizing a separate normalization layer, the [CLS] embeddings can better encode the global contextual information and are distributed more uniformly in its anisotropic space. When replacing the conventional normalization layer with the two separate layers, we observe an average 2.7% performance improvement over the image, natural language, and graph domains.more » « lessFree, publicly-accessible full text available December 10, 2024
-
Accurate prediction of dynamical systems in unstructured meshes has recently shown successes in scientific simulations. Many dynamical systems have a nonnegligible level of stochasticity introduced by various factors (e.g. chaoticity), so there is a need for a unified framework that captures both deterministic and stochastic components in the rollouts of these systems. Inspired by regeneration learning, we propose a new model that combines generative and sequential networks to model dynamical systems. Specifically, we use an autoencoder to learn compact representations of full-space physical variables in a low-dimensional space. We then integrate a transformer with a conditional normalizing flow model to model the temporal sequence of latent representations. We evaluate the new model in both deterministic and stochastic systems. The model outperforms several competitive baseline models and makes more accurate predictions of deterministic systems. Its own prediction error is also reflected in its uncertainty estimations. When predicting stochastic systems, the proposed model generates high-quality rollout samples. The mean and variance of these samples well match the statistics of samples computed from expensive numerical simulations.more » « less
-
Free, publicly-accessible full text available December 10, 2024
-
Diffusion-based graph generative models are effective in generating high-quality small graphs. However, it is hard to scale them to large graphs that contain thousands of nodes. In this work, we propose EDGE, a new diffusion-based graph generative model that addresses generative tasks for large graphs. The model is developed by reversing a discrete diffusion process that randomly removes edges until obtaining an empty graph. It leverages graph sparsity in the diffusion process to improve computational efficiency. In particular, EDGE only focuses on a small portion of graph nodes and only adds edges between these nodes. Without compromising modeling ability, it makes much fewer edge predictions than previous diffusion-based generative models. Furthermore, EDGE can explicitly model the node degrees of training graphs and then gain performance improvement in capturing graph statistics. The empirical study shows that EDGE is much more efficient than competing methods and can generate large graphs with thousands of nodes. It also outperforms baseline models in generation quality: graphs generated by the proposed model have graph statistics more similar to those of training graphs.more » « lessFree, publicly-accessible full text available July 23, 2024
-
Diffusion-based graph generative models are effective in generating high-quality small graphs. However, it is hard to scale them to large graphs that contain thousands of nodes. In this work, we propose EDGE, a new diffusion-based graph generative model that addresses generative tasks for large graphs. The model is developed by reversing a discrete diffusion process that randomly removes edges until obtaining an empty graph. It leverages graph sparsity in the diffusion process to improve computational efficiency. In particular, EDGE only focuses on a small portion of graph nodes and only adds edges between these nodes. Without compromising modeling ability, it makes much fewer edge predictions than previous diffusion-based generative models. Furthermore, EDGE can explicitly model the node degrees of training graphs and then gain performance improvement in capturing graph statistics. The empirical study shows that EDGE is much more efficient than competing methods and can generate large graphs with thousands of nodes. It also outperforms baseline models in generation quality: graphs generated by the proposed model have graph statistics more similar to those of training graphs.more » « lessFree, publicly-accessible full text available July 23, 2024
-
more » « less
Abstract Land rental markets are growing worldwide and facilitate efficient utilization of land. However, the short duration of occupancy and limited property rights mean that rental contracts may discourage longer-term sustainable land management. Direct investigation into the relationship between land tenure and ecological outcomes has been hampered by scale-appropriate data on land tenure, resource management, and land outcomes. In this paper, we address these issues with a study design that combines participatory mapping, household surveys, and remote sensing. We analyzed these data in a multilevel statistical model, controlling for environmental and land management influences. Our results show that rented land parcels are associated with worse rangeland outcomes compared to privately held parcels. This study contributes to the literature by documenting important empirical effects of rental markets and presenting a replicable workflow for integrating earth observations and micro-level survey data, which can be adopted by researchers and practitioners in regions where land registry data is unavailable or inaccessible. The results have important implications for incentive and compensatory-based environmental policy.
-
Zhou, Mingyuan (Ed.)We consider the problem of fitting autoregressive graph generative models via maximum likelihood estimation (MLE). MLE is intractable for graph autoregressive models because the nodes in a graph can be arbitrarily reordered; thus the exact likelihood involves a sum over all possible node orders leading to the same graph. In this work, we fit the graph models by maximizing a variational bound, which is built by first deriving the joint probability over the graph and the node order of the autoregressive process. This approach avoids the need to specify ad-hoc node orders, since an inference network learns the most likely node sequences that have generated a given graph. We improve the approach by developing a graph generative model based on attention mechanisms and an inference network based on routing search. We demonstrate empirically that fitting autoregressive graph models via variational inference improves their qualitative and quantitative performance, and the improved model and inference network further boost the performance. The implementation of the proposed model is publicly available at https://github.com/tufts-ml/Graph-Generation-MLE.more » « less
-
more » « less
Abstract Motivation While traditionally utilized for identifying site-specific metabolic activity within a compound to alter its interaction with a metabolizing enzyme, predicting the site-of-metabolism (SOM) is essential in analyzing the promiscuity of enzymes on substrates. The successful prediction of SOMs and the relevant promiscuous products has a wide range of applications that include creating extended metabolic models (EMMs) that account for enzyme promiscuity and the construction of novel heterologous synthesis pathways. There is therefore a need to develop generalized methods that can predict molecular SOMs for a wide range of metabolizing enzymes.
Results This article develops a Graph Neural Network (GNN) model for the classification of an atom (or a bond) being an SOM. Our model, GNN-SOM, is trained on enzymatic interactions, available in the KEGG database, that span all enzyme commission numbers. We demonstrate that GNN-SOM consistently outperforms baseline machine learning models, when trained on all enzymes, on Cytochrome P450 (CYP) enzymes, or on non-CYP enzymes. We showcase the utility of GNN-SOM in prioritizing predicted enzymatic products due to enzyme promiscuity for two biological applications: the construction of EMMs and the construction of synthesis pathways.
Availability and implementation A python implementation of the trained SOM predictor model can be found at https://github.com/HassounLab/GNN-SOM.
Supplementary information Supplementary data are available at Bioinformatics online.
-
Raia Hadsell ; Kyunghyun Cho ; Hugo Larochelle (Ed.)
Full Text Available