The latent subject: AI, recognition, and the politics of latent space

Transfer learning aims to leverage valuable information in one domain to promote the learning tasks in the other domain. Some recent studies indicated that the latent information, which has a close relationship with the high-level concepts, are more suitable for cross-domain text classification than learning raw features. To obtain more latent information existing in the latent feature space, some previous methods constructed multiple latent feature spaces. However, those methods ignored that the latent information of different latent spaces may lack the relevance for promoting the adaptability of transfer learning models, even may lead to negative knowledge transfer when there exists a glaring discrepancy among the different latent spaces. Additionally, since those methods learn the latent space distributions using a strategy of direct-promotion, their computational complexity increases exponentially as the number of latent spaces increases. To tackle this challenge, this paper proposes a Multiple Groups Transfer Learning (MGTL) method. MGTL first constructs multiple different latent feature spaces and then integrates the adjacent ones that have a similar latent feature dimension into one latent space group. Along this way, multiple latent space groups can be obtained. To enhance the relevance among these latent space groups, MGTL makes the adjacent groups contain one same latent space at least. Then, different groups will have more relevance than raw latent spaces. Second, MGTL utilizes an indirect-promotion strategy to connect different latent space groups. The computational complexity of MGTL increases linearly as the number of latent space groups increases and is superior to those multiple latent space methods based on direct-promotion. In addition, an iterative algorithm is proposed to solve the optimization problem. Finally, a set of systematic experiments demonstrate that MGTL outperforms all the compared existing methods.

Latent space representations learned through variational autoencoders (VAEs) offer a powerful, unsupervised means of capturing nonlinear structure in high-dimensional oncology data. The latent embedding spaces often encode information that differs from traditional bioinformatics methods such as t-SNE or UMAP. However, a persistent challenge remains: how to meaningfully visualize and interpret these latent variables. Common dimensionality reduction techniques like UMAP and t-SNE, while effective, can obscure graph-theoretic relationships that may underlie important biological patterns. We present a novel approach for intuitive latent space interpretation using NetFlow, a method that visualizes the organizational structure of samples as a graph derived from their latent embeddings. NetFlow constructs a topological representation based on the metric structure of the latent space, drawing on concepts from network analysis, optimal mass transport, topological data analysis, and lineage tracing. The result is an interpretable graph in which nodes represent individual subjects and edges reflect local and global similarity among the samples. We applied this method to multiple myeloma (MM), a hematologic malignancy marked by malignant plasma cell proliferation and inevitable relapse. To uncover hidden disease subtypes, we trained a VAE on multimodal data from 659 patients in the MMRF CoMMpass dataset (IA19), integrating transcriptomic, genomic, and clinical features. Direct clustering of latent space vectors failed to yield subgroups with significant differences in progression-free survival (PFS). In contrast, NetFlow generated a latent space graph that, when clustered using Louvain community detection, identified three distinct subtypes: one high-risk and two low-risk groups. The high-risk group exhibited a median PFS of 1.5 years shorter than the low-risk groups (p<0.001) and was enriched for known poor prognostic markers including gain 1q21 (59%), MAF translocations (17%), and t(4;14) (66%). Although the two low-risk groups had similar PFS outcomes, they differed in their molecular profiles, suggesting they may benefit from different therapeutic strategies. These preliminary results demonstrate that variational autoencoders and NetFlow graph analysis can reveal latent substructures missed by traditional clustering, thereby advancing latent space explainability and enabling improved subtype discovery in MM. Our framework offers a generalizable pipeline for interpreting deep generative models in cancer genomics. Citation Format: Anish K. Simhal, Rena Elkin, Ross S. Firestone, Jung Hun Oh, Joseph O. Deasy. Unsupervised graph-based visualization of variational autoencoder latent spaces reveals hidden multiple myeloma subtypes [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Artificial Intelligence and Machine Learning; 2025 Jul 10-12; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(13_Suppl):Abstract nr A031.

Decision letter: Model-based whole-brain perturbational landscape of neurodegenerative diseases

Editor's evaluation: Model-based whole-brain perturbational landscape of neurodegenerative diseases

The estimation of bit wear during real-time operation plays a crucial role in bit trip planning and drilling optimization. Estimates by human learnings can be highly subjective and convoluted by changes in formation and drilling data. Conventional methods using physics-based model and supervised machine learning are time consuming and accuracy is significantly limited by the labelled data available. Moreover, those approaches do not consider the entire real-time time/depth series. In this study, we present a real-time field-validated bit agnostic wear model using unsupervised deep learning method to overcome these challenges. The framework is of unsupervised learning and representation of LWD sub-/surface drilling data) time/depth series data to lower-dimensional representation (latent) space with reconstruction ability and facilitating the downstream task e.g., bit wear estimation. Specifically, a bi-directional Long short-term Memory-based Variational Autoencoder (biLSTM-VAE) projects raw drilling data into a latent space in which the real-time bit-wear can be estimated through classification of the incoming real time data in the latent space. The deep neural network was trained in an unsupervised manner and the bit-wear estimation is an end-to-end process, and then implemented for evaluation in a real time lateral. The model training results had significant separation of bit-wear states in the lower dimensional latent space projected by the trained model, suggesting the feasibility of the real-time monitoring and tracking of bit wear states in the latent space. We then employed the trained deep learning model to estimate the bit wear in the real-time drilling for seven runs in a lateral. The predicted bit wear for all evaluation field runs were closely match the actual dull grade with the error smaller than 1.0. Among the seven prediction values, five of them agreed exactly with the actual field dull grading. Moreover, real time data of bits from different manufacturers and their results demonstrate the model to be bit-agnostic. To the best of our knowledge, this is the first field implementation of AI-assisted model for the real-time bit wear estimation that is both trained in an unsupervised manner in end-to-end process and AI predicted on completely unseen time/depth series data. Moreover, commonly available real time data is selected to ensure ease of applicability. Our approach also introduces a novel method of estimating bit wear based on the tracking of its trajectory in the latent space including the memory as opposed to isolated events. This helps improve the efficiency in drilling operations and can significantly affect economics of well engineering. As compared to traditional physic-based models that have been applied to estimate the bit wear, the proposed AI model is bit agnostic and is applicable to wide range of applications for drilling optimization

Online users are typically active on multiple social media networks (SMNs), which constitute a multiplex social network. With improvements in cybersecurity awareness, users increasingly choose different usernames and provide different profiles on different SMNs. Thus, it is becoming increasingly challenging to determine whether given accounts on different SMNs belong to the same user; this can be expressed as an interlayer link prediction problem in a multiplex network. To address the challenge of predicting interlayer links, feature or structure information is leveraged. Existing methods that use network embedding techniques to address this problem focus on learning a mapping function to unify all nodes into a common latent representation space for prediction; positional relationships between unmatched nodes and their common matched neighbors (CMNs) are not utilized. Furthermore, the layers are often modeled as unweighted graphs, ignoring the strengths of the relationships between nodes. To address these limitations, we propose a framework based on multiple types of consistency between embedding vectors (MulCEVs). In MulCEV, the traditional embedding-based method is applied to obtain the degree of consistency between the vectors representing the unmatched nodes, and a proposed distance consistency index based on the positions of nodes in each latent space provides additional clues for prediction. By associating these two types of consistency, the effective information in the latent spaces is fully utilized. In addition, MulCEV models the layers as weighted graphs to obtain representation. In this way, the higher the strength of the relationship between nodes, the more similar their embedding vectors in the latent representation space will be. The results of our experiments on several real-world and synthetic datasets demonstrate that the proposed MulCEV framework markedly outperforms current embedding-based methods, especially when the number of training iterations is small.

One problem in real-world applications of reinforcement learning is the high dimensionality of the action search spaces, which comes from the combination of actions over time. To reduce the dimensionality of action sequence search spaces, macro actions have been studied, which are sequences of primitive actions to solve tasks. However, previous studies relied on humans to define macro actions or assumed macro actions to be repetitions of the same primitive actions. We propose encoded action sequence reinforcement learning (EASRL), a reinforcement learning method that learns flexible sequences of actions in a latent space for a high-dimensional action sequence search space. With EASRL, encoder and decoder networks are trained with demonstration data by using variational autoencoders for mapping macro actions into the latent space. Then, we learn a policy network in the latent space, which is a distribution over encoded macro actions given a state. By learning in the latent space, we can reduce the dimensionality of the action sequence search space and handle various patterns of action sequences. We experimentally demonstrate that the proposed method outperforms other reinforcement learning methods on tasks that require an extensive amount of search.

Deep neural networks are good at extracting low-dimensional subspaces (latent spaces) that represent the essential features inside a high-dimensional dataset. Deep generative models represented by variational autoencoders (VAEs) can generate and infer high-quality datasets, such as images. In particular, VAEs can eliminate the noise contained in an image by repeating the mapping between latent and data space. To clarify the mechanism of such denoising, we numerically analyzed how the activity pattern of trained networks changes in the latent space during inference. We considered the time development of the activity pattern for specific data as one trajectory in the latent space and investigated the collective behavior of these inference trajectories for many data. Our study revealed that when a cluster structure exists in the dataset, the trajectory rapidly approaches the center of the cluster. This behavior was qualitatively consistent with the concept retrieval reported in associative memory models. Additionally, the larger the noise contained in the data, the closer the trajectory was to a more global cluster. It was demonstrated that by increasing the number of the latent variables, the trend of the approach a cluster center can be enhanced, and the generalization ability of the VAE can be improved.

Manifold adversarial training for supervised and semi-supervised learning

The design of a new therapeutic agent is a time-consuming and expensive process. The rise of machine intelligence provides a grand opportunity of expeditiously discovering novel drug candidates through smart search in the vast molecular structural space. In this paper, we propose a new approach called adversarial deep evolutionary learning (ADEL) to search for novel molecules in the latent space of an adversarial generative model and keep improving the latent representation space. In ADEL, a custom-made adversarial autoencoder (AAE) model is developed and trained under a deep evolutionary learning (DEL) process. This involves an initial training of the AAE model, followed by an integration of multi-objective evolutionary optimization in the continuous latent representation space of the AAE rather than the discrete structural space of molecules. By using the AAE, an arbitrary distribution can be provided to the training of AAE such that the latent representation space is set to that distribution. This allows for a starting latent space from which new samples can be produced. Throughout the process of learning, new samples of high-quality are generated after each iteration of training and then added back into the full dataset. Therefore, allowing for a more comprehensive procedure of understanding the data structure. This combination of evolving data and continuous learning not only enables improvement in the generative model, but the data as well. By comparing ADEL to the previous work in DEL, we see that ADEL can obtain better property distributions.

Graph convolutional networks (GCNs) emerge as the most successful learning models for graph-structured data. Despite their success, existing GCNs usually ignore the entangled latent factors typically arising in real-world graphs, which results in nonexplainable node representations. Even worse, while the emphasis has been placed on local graph information, the global knowledge of the entire graph is lost to a certain extent. In this work, to address these issues, we propose a novel framework for GCNs, termed LGD-GCN, taking advantage of both local and global information for disentangling node representations in the latent space. Specifically, we propose to represent a disentangled latent continuous space with a statistical mixture model, by leveraging neighborhood routing mechanism locally. From the latent space, various new graphs can then be disentangled and learned, to overall reflect the hidden structures with respect to different factors. On the one hand, a novel regularizer is designed to encourage interfactor diversity for model expressivity in the latent space. On the other hand, the factor-specific information is encoded globally via employing a message passing along these new graphs, in order to strengthen intrafactor consistency. Extensive evaluations on both synthetic and five benchmark datasets show that LGD-GCN brings significant performance gains over the recent competitive models in both disentangling and node classification. Particularly, LGD-GCN is able to outperform averagely the disentangled state-of-the-arts by 7.4% on social network datasets.

Given a message, cascade prediction aims to predict the individuals who will potentially retweet it. Most existing methods either exploit demographical, structural, and temporal features for prediction, or explicitly rely on particular information diffusion models. Recently, researchers attempt to design fully data-driven methods for cascade prediction (i.e., without requiring human-defined features or information diffusion models), directly leveraging historical cascades to learn interpersonal proximity and then making prediction based on the learned proximity. One widely-used method to represent interpersonal proximity is social embedding, i.e., each individual is embedded into a low-dimensional latent metric space. One challenging problem is to design cost-effective method to learn social embedding from cascades. In this paper, we propose a position-aware asymmetric embedding method to effectively learn social embedding for cascade prediction. Different from existing methods where individuals are embedded into a single latent space, our method embeds each individual into two latent spaces: a latent influence space and a latent susceptibility space. Furthermore, our method employs the occurrence position of individuals in cascades to improve the learning efficiency of social embedding. We validate the proposed method on a dataset extracted from Sina Weibo. Experimental results demonstrate that the proposed model outperforms state-of-the-art social embedding methods at both learning efficiency and prediction accuracy.

A regularity augmented evolutionary algorithm with dual-space search for multiobjective optimization

Facial expression is the crucial component for human beings to express their mental state and it has become one of the prominent areas of research in computer vision. However, the task becomes challenging when the given facial image is non-frontal. The influence of poses on facial images is alleviated using an encoder of a generative adversarial network capable of learning pose invariant representations. State-of-art results for image generation are achieved using styleGAN architecture. An efficient model is proposed to embed the given image into the latent vector space of styleGAN. The encoder extracts high-level features of the facial image and encodes them into the latent space. Rigorous analysis of semantics hidden in the latent space of styleGAN is performed. Based on the analysis, the facial image is synthesized, and facial expressions are recognized using an expression recognition neural network. The original image is recovered from the features encoded in the latent space. Semantic editing operations like face rotation, style transfer, face aging, image morphing and expression transfer can be performed on the image obtained from the image generated using the features encoded latent space of styleGAN. L2 feature-wise loss is applied to warrant the quality of the rebuilt image. The facial image is then fed into the attribute classifier to extract high-level features, and the features are concatenated to perform facial expression classification. Evaluations are performed on the generated results to demonstrate that state-of-art results are achieved using the proposed method.

Adversarial deep evolutionary learning for drug design