Search for: All records

Learning disentangled causal representations is a challenging problem that has gained significant attention recently due to its implications for extracting meaningful information for downstream tasks. In this work, we define a new notion of causal disentanglement from the perspective of independent causal mechanisms. We propose ICM-VAE, a framework for learning causally disentangled representations supervised by causally related observed labels. We model causal mechanisms using nonlinear learnable flow-based diffeomorphic functions to map noise variables to latent causal variables. Further, to promote the disentanglement of causal factors, we propose a causal disentanglement prior learned from auxiliary labels and the latent causal structure. We theoretically show the identifiability of causal factors and mechanisms up to permutation and elementwise reparameterization. We empirically demonstrate that our framework induces highly disentangled causal factors, improves interventional robustness, and is compatible with counterfactual generation.

 

The fairness-aware online learning framework has emerged as a potent tool within the context of continuous lifelong learning. In this scenario, the learner’s objective is to progressively acquire new tasks as they arrive over time, while also guaranteeing statistical parity among various protected sub-populations, such as race and gender when it comes to the newly introduced tasks. A significant limitation of current approaches lies in their heavy reliance on the i.i.d (independent and identically distributed) assumption concerning data, leading to a static regret analysis of the framework. Nevertheless, it’s crucial to note that achieving low static regret does not necessarily translate to strong performance in dynamic environments characterized by tasks sampled from diverse distributions. In this article, to tackle the fairness-aware online learning challenge in evolving settings, we introduce a unique regret measure, FairSAR, by incorporating long-term fairness constraints into a strongly adapted loss regret framework. Moreover, to determine an optimal model parameter at each time step, we introduce an innovative adaptive fairness-aware online meta-learning algorithm, referred to as FairSAOML. This algorithm possesses the ability to adjust to dynamic environments by effectively managing bias control and model accuracy. The problem is framed as a bi-level convex-concave optimization, considering both the model’s primal and dual parameters, which pertain to its accuracy and fairness attributes, respectively. Theoretical analysis yields sub-linear upper bounds for both loss regret and the cumulative violation of fairness constraints. Our experimental evaluation of various real-world datasets in dynamic environments demonstrates that our proposed FairSAOML algorithm consistently outperforms alternative approaches rooted in the most advanced prior online learning methods.

 

Hyperspectral imaging (HSI) technology captures spectral information across a broad wavelength range, providing richer pixel features compared to traditional color images with only three channels. Although pixel classification in HSI has been extensively studied, especially using graph convolution neural networks (GCNs), quantifying epistemic and aleatoric uncertainties associated with the HSI classification (HSIC) results remains an unexplored area. These two uncertainties are effective for out-of-distribution (OOD) and misclassification detection, respectively. In this paper, we adapt two advanced uncertainty quantification models, evidential GCNs (EGCN) and graph posterior networks (GPN), designed for node classifications in graphs, into the realm of HSIC. We first reveal theoretically that a popular uncertainty cross-entropy (UCE) loss function is insufficient to produce good epistemic uncertainty when learning EGCNs. To mitigate the limitations, we propose two regularization terms. One leverages the inherent property of HSI data where each feature vector is a linear combination of the spectra signatures of the confounding materials, while the other is the total variation (TV) regularization to enforce the spatial smoothness of the evidence with edge-preserving. We demonstrate the effectiveness of the proposed regularization terms on both EGCN and GPN on three real-world HSIC datasets for OOD and misclassification detection tasks. 

During the bloom season, the colonial cyanobacteriumMicrocystisforms complex aggregates which include a diverse microbiome within an exopolymer matrix. Early research postulated a simple mutualism existing with bacteria benefitting from the rich source of fixed carbon andMicrocystisreceiving recycled nutrients. Researchers have since hypothesized thatMicrocystisaggregates represent a community of synergistic and interacting species, an interactome, each with unique metabolic capabilities that are critical to the growth, maintenance, and demise ofMicrocystisblooms. Research has also shown that aggregate-associated bacteria are taxonomically different from free-living bacteria in the surrounding water. Moreover, research has identified little overlap in functional potential betweenMicrocystisand members of its microbiome, further supporting the interactome concept. However, we still lack verification of general interaction and know little about the taxa and metabolic pathways supporting nutrient and metabolite cycling withinMicrocystisaggregates.

During a 7-month study of bacterial communities comparing free-living and aggregate-associated bacteria in Lake Taihu, China, we found that aerobic anoxygenic phototrophic (AAP) bacteria were significantly more abundant withinMicrocystisaggregates than in free-living samples, suggesting a possible functional role for AAP bacteria in overall aggregate community function. We then analyzed gene composition in 102 high-quality metagenome-assembled genomes (MAGs) of bloom-microbiome bacteria from 10 lakes spanning four continents, compared with 12 completeMicrocystisgenomes which revealed that microbiome bacteria andMicrocystispossessed complementary biochemical pathways that could serve in C, N, S, and P cycling. Mapping published transcripts fromMicrocystisblooms onto a comprehensive AAP and non-AAP bacteria MAG database (226 MAGs) indicated that observed high levels of expression of genes involved in nutrient cycling pathways were in AAP bacteria.

Our results provide strong corroboration of the hypothesizedMicrocystisinteractome and the first evidence that AAP bacteria may play an important role in nutrient cycling withinMicrocystisaggregate microbiomes.

 

Deep learning’s performance has been extensively recognized recently. Graph neural networks (GNNs) are designed to deal with graph-structural data that classical deep learning does not easily manage. Since most GNNs were created using distinct theories, direct comparisons are impossible. Prior research has primarily concentrated on categorizing existing models, with little attention paid to their intrinsic connections. The purpose of this study is to establish a unified framework that integrates GNNs based on spectral graph and approximation theory. The framework incorporates a strong integration between spatial- and spectral-based GNNs while tightly associating approaches that exist within each respective domain.

 

Fundamental differences in DOM composition at the Bermuda Atlantic time series (BATS) stationversusthe Hawai’i time series station ALOHA.

 

Deep neural networks (DNNs) have been shown to perform well on exclusive, multi-class classification tasks. However, when different classes have similar visual features, it becomes challenging for human annotators to differentiate them. This scenario necessitates the use of composite class labels. In this paper, we propose a novel framework called Hyper-Evidential Neural Network (HENN) that explicitly models predictive uncertainty due to composite class labels in training data in the context of the belief theory called Subjective Logic (SL). By placing a grouped Dirichlet distribution on the class probabilities, we treat predictions of a neural network as parameters of hyper-subjective opinions and learn the network that collects both single and composite evidence leading to these hyper-opinions by a deterministic DNN from data. We introduce a new uncertainty type called vagueness originally designed for hyper-opinions in SL to quantify composite classification uncertainty for DNNs. Our results demonstrate that HENN outperforms its state-of-the-art counterparts based on four image datasets. The code and datasets are available at: https://github.com/ Hugo101/HyperEvidentialNN.