Siyuan Gao

In this paper, we introduce a novel framework following an upstream-downstream paradigm to construct user and item (Pin) embeddings from diverse data sources, which are essential for Pinterest to deliver personalized Pins and ads effectively. Our upstream models are trained on extensive data sources featuring varied signals, utilizing complex architectures to capture intricate relationships between users and Pins on Pinterest. To ensure scalability of the upstream models, entity embeddings are learned, and regularly refreshed, rather than real-time computation, allowing for asynchronous interaction between the upstream and downstream models. These embeddings are then integrated as input features in numerous downstream tasks, including ad retrieval and ranking models for CTR and CVR predictions. We demonstrate that our framework achieves notable performance improvements in both offline and online settings across various downstream tasks. This framework has been deployed in Pinterest’s production ad ranking systems, resulting in significant gains in online metrics.

Social networks are prosperous marketplaces where creators and consumers congregate to share and consume various content. In general, products that rank content for distribution (such as newsfeeds, stories, and notifications) and are related to edge recommendations (such as connect to members, follow celebrities or groups or hashtags) optimize the experience of active users. Typically, such users generate ample interaction data amenable to accurate model training and prediction. In contrast, we prioritize enhancing the experience of inactive members (IMs) who do not have a rich connection network. We formulate strategies for recommending superior edges to help members grow their connection network. Adapting the recommendations provides enormous value to the IMs and can significantly influence their future behaviour and engagement with the ecosystem. To that end, we propose a general and scalable multi-objective optimization (MOO) framework to provide more value to IMs as invitation recipients on LinkedIn, a professional network with over 900M members. To deal with the enormous scale, we formulate the problem as a massive constrained linear optimization involving billions of variables and millions of constraints and efficiently solve it using accelerated gradient descent, making this the largest deployment of LP-based recommender systems worldwide. Furthermore, the proposed MOO paradigm can solve the general problem of matching different types of entities in an m-sided marketplace. Finally, we discuss the challenges and benefits of implementing and ramping our method in production at scale at LinkedIn and report our findings about the core business metrics related to users’ engagement and network health.

Functional connectivity (FC) estimated from functional magnetic resonance imaging (fMRI) signals is important in understanding neural representation and information processing in cortical networks. However, due to a lack of "ground truth" FC pattern, the reliability and robustness of FC estimates are usually examined in downstream FC analysis tasks, such as performing participant’s identification (also known as "fingerprinting"). In this paper, we propose to learn FC via a smooth graph learning framework. In particular, we treat each time frame of the fMRI time series as a graph signal on an underlying functional brain graph, and estimate the smooth graph functional connectivity (SGFC) by learning the weighted graph adjacency matrix based on graph signal smoothness assumption. We demonstrate that our approach gives rise to a natural and sparse graph representation of FC from which reliable graph measures can be extracted. Reliability of SGFC is evaluated in the context of fingerprinting and compared to correlation FC (CFC). SGFC achieves higher fingerprinting accuracy across several different experiment settings; the improvement is even more significant when a shorter fMRI scanning length is used for FC estimation. In addition to being reliable, we also validate the cognitive relevance of SGFC by using it to predict fluid intelligence. Finally, in evaluating topological measures of the sparse graph, SGFC reveals a more small-world and modular structure compared to CFC. Together, our results suggest that the smooth graph learning framework produces a naturally sparse, reliable, and cognitive-relevant representation of functional connectivity.

Large-scale brain dynamics are believed to lie in a latent, low-dimensional space. Typically, the embeddings of brain scans are derived independently from different cognitive tasks or resting-state data, ignoring a potentially large—and shared—portion of this space. Here, we establish that a shared, robust, and interpretable low-dimensional space of brain dynamics can be recovered from a rich repertoire of task-based functional magnetic resonance imaging (fMRI) data. This occurs when relying on nonlinear approaches as opposed to traditional linear methods. The embedding maintains proper temporal progression of the tasks, revealing brain states and the dynamics of network integration. We demonstrate that resting-state data embeds fully onto the same task embedding, indicating similar brain states are present in both task and resting-state data. Our findings suggest analysis of fMRI data from multiple cognitive tasks in a low-dimensional space is possible and desirable.

Large datasets that enable researchers to perform investigations with unprecedented rigor are growing increasingly common in neuroimaging. Due to the simultaneous increasing popularity of open science, these state-of-the-art datasets are more accessible than ever to researchers around the world. While analysis of these samples has pushed the field forward, they pose a new set of challenges that might cause difficulties for novice users. Here we offer practical tips for working with large datasets from the end-user’s perspective. We cover all aspects of the data lifecycle: from what to consider when downloading and storing the data to tips on how to become acquainted with a dataset one did not collect and what to share when communicating results. This manuscript serves as a practical guide one can use when working with large neuroimaging datasets, thus dissolving barriers to scientific discovery.

Resting-state and task-based functional connectivity matrices, or connectomes, are powerful predictors of individual differences in phenotypic measures. However, most of the current state-of-the-art algorithms only build predictive models based on a single connectome for each individual. This approach neglects the complementary information contained in connectomes from different sources and reduces prediction performance. In order to combine different task connectomes into a single predictive model in a principled way, we propose a novel prediction framework, termed multidimensional connectome-based predictive modeling. Two specific algorithms are developed and implemented under this framework. Using two large open-source datasets with multiple tasks—the Human Connectome Project and the Philadelphia Neurodevelopmental Cohort, we validate and compare our framework against performing connectome-based predictive modeling (CPM) on each task connectome independently, CPM on a general functional connectivity matrix created by averaging together all task connectomes for an individual, and CPM with a naive extension to multiple connectomes where each edge for each task is selected independently. Our framework exhibits superior performance in prediction compared with the other competing methods. We found that different tasks contribute differentially to the final predictive model, suggesting that the battery of tasks used in prediction is an important consideration.

Recent work has begun to relate individual differences in brain functional organization to human behaviors and cognition, but the best brain state to reveal such relationships remains an open question. In two large, independent data sets, we here show that cognitive tasks amplify trait-relevant individual differences in patterns of functional connectivity, such that predictive models built from task fMRI data outperform models built from resting-state fMRI data. Further, certain tasks consistently yield better predictions of fluid intelligence than others, and the task that generates the best-performing models varies by sex. By considering task-induced brain state and sex, the best-performing model explains over 20% of the variance in fluid intelligence scores, as compared to <6% of variance explained by rest-based models. This suggests that identifying and inducing the right brain state in a given group can better reveal brain-behavior relationships, motivating a paradigm shift from rest- to task-based functional connectivity analyses.