Machine Learning (cs.LG)

Abstract: While deep reinforcement learning has shown important empirical success, it tends to learn relatively slow due to slow propagation of rewards information and slow update of parametric neural networks. Non-parametric episodic memory, on the other hand, provides a faster learning alternative that does not require representation learning and uses maximum episodic return as state-action values for action selection. Episodic memory and reinforcement learning both have their own strengths and weaknesses. Notably, humans can leverage multiple memory systems concurrently during learning and benefit from all of them. In this work, we propose a method called Two-Memory reinforcement learning agent (2M) that combines episodic memory and reinforcement learning to distill both of their strengths. The 2M agent exploits the speed of the episodic memory part and the optimality and the generalization capacity of the reinforcement learning part to complement each other. Our experiments demonstrate that the 2M agent is more data efficient and outperforms both pure episodic memory and pure reinforcement learning, as well as a state-of-the-art memory-augmented RL agent. Moreover, the proposed approach provides a general framework that can be used to combine any episodic memory agent with other off-policy reinforcement learning algorithms.

Abstract: Federated learning has attracted increasing attention due to the promise of balancing privacy and large-scale learning; numerous approaches have been proposed. However, most existing approaches focus on problems with balanced data, and prediction performance is far from satisfactory for many real-world applications where the number of samples in different classes is highly imbalanced. To address this challenging problem, we developed a novel federated learning method for imbalanced data by directly optimizing the area under curve (AUC) score. In particular, we formulate the AUC maximization problem as a federated compositional minimax optimization problem, develop a local stochastic compositional gradient descent ascent with momentum algorithm, and provide bounds on the computational and communication complexities of our algorithm. To the best of our knowledge, this is the first work to achieve such favorable theoretical results. Finally, extensive experimental results confirm the efficacy of our method.

Abstract: Although procurement fraud is always a critical problem in almost every free market, audit departments still have a strong reliance on reporting from informed sources when detecting them. With our generous cooperator, SF Express, sharing the access to the database related with procurements took place from 2015 to 2017 in their company, our team studies how machine learning techniques could help with the audition of one of the most profound crime among current chinese market, namely procurement frauds. By representing each procurement event as 9 specific features, we construct neural network models to identify suspicious procurements and classify their fraud types. Through testing our models over 50000 samples collected from the procurement database, we have proven that such models -- despite having space for improvements -- are useful in detecting procurement frauds.

Abstract: Graph neural networks (GNN) suffer from severe inefficiency. It is mainly caused by the exponential growth of node dependency with the increase of layers. It extremely limits the application of stochastic optimization algorithms so that the training of GNN is usually time-consuming. To address this problem, we propose to decouple a multi-layer GNN as multiple simple modules for more efficient training, which is comprised of classical forward training (FT)and designed backward training (BT). Under the proposed framework, each module can be trained efficiently in FT by stochastic algorithms without distortion of graph information owing to its simplicity. To avoid the only unidirectional information delivery of FT and sufficiently train shallow modules with the deeper ones, we develop a backward training mechanism that makes the former modules perceive the latter modules. The backward training introduces the reversed information delivery into the decoupled modules as well as the forward information delivery. To investigate how the decoupling and greedy training affect the representational capacity, we theoretically prove that the error produced by linear modules will not accumulate on unsupervised tasks in most cases. The theoretical and experimental results show that the proposed framework is highly efficient with reasonable performance.

Abstract: Large-scale pre-trained models have achieved remarkable success in a variety of scenarios and applications, but how to leverage them to improve the prediction reliability of downstream models is undesirably under-explored. Moreover, modern neural networks have been found to be poorly calibrated and make overconfident predictions regardless of inherent sample difficulty and data uncertainty. To address this issue, we propose to utilize large-scale pre-trained models to guide downstream model training with sample difficulty-aware entropy regularization. Pre-trained models that have been exposed to large-scale datasets and do not overfit the downstream training classes enable us to measure each training sample difficulty via feature-space Gaussian modeling and relative Mahalanobis distance computation. Importantly, by adaptively penalizing overconfident prediction based on the sample's difficulty, we simultaneously improve accuracy and uncertainty calibration on various challenging benchmarks, consistently surpassing competitive baselines for reliable prediction.

Abstract: The K Nearest Neighbors (KNN) classifier is widely used in many fields such as fingerprint-based localization or medicine. It determines the class membership of unlabelled sample based on the class memberships of the K labelled samples, the so-called nearest neighbors, that are closest to the unlabelled sample. The choice of K has been the topic of various studies and proposed KNN-variants. Yet no variant has been proven to outperform all other variants. In this paper a new KNN-variant is proposed which ensures that the K nearest neighbors are indeed close to the unlabelled sample and finds K along the way. The proposed algorithm is tested and compared to the standard KNN in theoretical scenarios and for indoor localization based on ion-mobility spectrometry fingerprints. It achieves a higher classification accuracy than the KNN in the tests, while requiring having the same computational demand.

Abstract: Several algorithms for learning the structure of dynamic Bayesian networks (DBNs) require an a priori ordering of variables, which influences the determined graph topology. However, it is often unclear how to determine this order if feature importance is unknown, especially as an exhaustive search is usually impractical. In this paper, we introduce Ranking Approaches for Unknown Structures (RAUS), an automated framework to systematically inform variable ordering and learn networks end-to-end. RAUS leverages existing statistical methods (Cramers V, chi-squared test, and information gain) to compare variable ordering, resultant generated network topologies, and DBN performance. RAUS enables end-users with limited DBN expertise to implement models via command line interface. We evaluate RAUS on the task of predicting impending acute kidney injury (AKI) from inpatient clinical laboratory data. Longitudinal observations from 67,460 patients were collected from our electronic health record (EHR) and Kidney Disease Improving Global Outcomes (KDIGO) criteria were then applied to define AKI events. RAUS learns multiple DBNs simultaneously to predict a future AKI event at different time points (i.e., 24-, 48-, 72-hours in advance of AKI). We also compared the results of the learned AKI prediction models and variable orderings to baseline techniques (logistic regression, random forests, and extreme gradient boosting). The DBNs generated by RAUS achieved 73-83% area under the receiver operating characteristic curve (AUCROC) within 24-hours before AKI; and 71-79% AUCROC within 48-hours before AKI of any stage in a 7-day observation window. Insights from this automated framework can help efficiently implement and interpret DBNs for clinical decision support. The source code for RAUS is available in GitHub at https://github.com/dgrdn08/RAUS .

Abstract: Questions remain on the robustness of data-driven learning methods when crossing the gap from simulation to reality. We utilize weight anchoring, a method known from continual learning, to cultivate and fixate desired behavior in Neural Networks. Weight anchoring may be used to find a solution to a learning problem that is nearby the solution of another learning problem. Thereby, learning can be carried out in optimal environments without neglecting or unlearning desired behavior. We demonstrate this approach on the example of learning mixed QoS-efficient discrete resource scheduling with infrequent priority messages. Results show that this method provides performance comparable to the state of the art of augmenting a simulation environment, alongside significantly increased robustness and steerability.

Abstract: Continual learning aims to learn on non-stationary data streams without catastrophically forgetting previous knowledge. Prevalent replay-based methods address this challenge by rehearsing on a small buffer holding the seen data, for which a delicate sample selection strategy is required. However, existing selection schemes typically seek only to maximize the utility of the ongoing selection, overlooking the interference between successive rounds of selection. Motivated by this, we dissect the interaction of sequential selection steps within a framework built on influence functions. We manage to identify a new class of second-order influences that will gradually amplify incidental bias in the replay buffer and compromise the selection process. To regularize the second-order effects, a novel selection objective is proposed, which also has clear connections to two widely adopted criteria. Furthermore, we present an efficient implementation for optimizing the proposed criterion. Experiments on multiple continual learning benchmarks demonstrate the advantage of our approach over state-of-the-art methods. Code is available at https://github.com/feifeiobama/InfluenceCL.

Abstract: As operating frequencies and clock speeds in processors have increased over the years, interconnects affect both the reliability and performance of entire electronic systems. Fault detection and diagnosis of the interconnects are crucial for prognostics and health management (PHM) of electronics. However, existing research works utilizing electrical signals as prognostic factors have limitations, such as the inability to distinguish the root cause of defects, which eventually requires additional destructive evaluation, and vulnerability to noise that results in a false alarm. Herein, we realize the non-destructive detection and diagnosis of defects in Cu interconnects, achieving early detection, high diagnostic accuracy, and noise robustness. To the best of our knowledge, this study first simultaneously analyzes the root cause and severity using electrical signal patterns. In this paper, we experimentally show that S-parameter patterns have the ability for fault diagnosis and they are effective input data for learning algorithms. Furthermore, we propose a novel severity rating ensemble learning (SREL) approach to enhance diagnostic accuracy and noise-robustness. Our method, with a maximum accuracy of 99.3%, outperforms conventional machine learning and multi-class convolutional neural networks (CNN) as additional noise levels increase.

Abstract: With the recent rise of neural operators, scientific machine learning offers new solutions to quantify uncertainties associated with high-fidelity numerical simulations. Traditional neural networks, such as Convolutional Neural Networks (CNN) or Physics-Informed Neural Networks (PINN), are restricted to the prediction of solutions in a predefined configuration. With neural operators, one can learn the general solution of Partial Differential Equations, such as the elastic wave equation, with varying parameters. There have been very few applications of neural operators in seismology. All of them were limited to two-dimensional settings, although the importance of three-dimensional (3D) effects is well known. In this work, we apply the Fourier Neural Operator (FNO) to predict ground motion time series from a 3D geological description. We used a high-fidelity simulation code, SEM3D, to build an extensive database of ground motions generated by 30,000 different geologies. With this database, we show that the FNO can produce accurate ground motion even when the underlying geology exhibits large heterogeneities. Intensity measures at moderate and large periods are especially well reproduced. We present the first seismological application of Fourier Neural Operators in 3D. Thanks to the generalizability of our database, we believe that our model can be used to assess the influence of geological features such as sedimentary basins on ground motion, which is paramount to evaluating site effects.

Abstract: Partially-observable problems pose a trade-off between reducing costs and gathering information. They can be solved optimally by planning in belief space, but that is often prohibitively expensive. Model-predictive control (MPC) takes the alternative approach of using a state estimator to form a belief over the state, and then plan in state space. This ignores potential future observations during planning and, as a result, cannot actively increase or preserve the certainty of its own state estimate. We find a middle-ground between planning in belief space and completely ignoring its dynamics by only reasoning about its future accuracy. Our approach, filter-aware MPC, penalises the loss of information by what we call "trackability", the expected error of the state estimator. We show that model-based simulation allows condensing trackability into a neural network, which allows fast planning. In experiments involving visual navigation, realistic every-day environments and a two-link robot arm, we show that filter-aware MPC vastly improves regular MPC.

Abstract: The recent rise in popularity of Hyperparameter Optimization (HPO) for deep learning has highlighted the role that good hyperparameter (HP) space design can play in training strong models. In turn, designing a good HP space is critically dependent on understanding the role of different HPs. This motivates research on HP Importance (HPI), e.g., with the popular method of functional ANOVA (f-ANOVA). However, the original f-ANOVA formulation is inapplicable to the subspaces most relevant to algorithm designers, such as those defined by top performance. To overcome this problem, we derive a novel formulation of f-ANOVA for arbitrary subspaces and propose an algorithm that uses Pearson divergence (PED) to enable a closed-form computation of HPI. We demonstrate that this new algorithm, dubbed PED-ANOVA, is able to successfully identify important HPs in different subspaces while also being extremely computationally efficient.

Abstract: Trust is a crucial factor affecting the adoption of machine learning (ML) models. Qualitative studies have revealed that end-users, particularly in the medical domain, need models that can express their uncertainty in decision-making allowing users to know when to ignore the model's recommendations. However, existing approaches for quantifying decision-making uncertainty are not model-agnostic, or they rely on complex statistical derivations that are not easily understood by laypersons or end-users, making them less useful for explaining the model's decision-making process. This work proposes a set of class-independent meta-heuristics that can characterize the complexity of an instance in terms of factors are mutually relevant to both human and ML decision-making. The measures are integrated into a meta-learning framework that estimates the risk of misclassification. The proposed framework outperformed predicted probabilities in identifying instances at risk of being misclassified. The proposed measures and framework hold promise for improving model development for more complex instances, as well as providing a new means of model abstention and explanation.

Abstract: Few-shot relation reasoning on knowledge graphs (FS-KGR) aims to infer long-tail data-poor relations, which has drawn increasing attention these years due to its practicalities. The pre-training of previous methods needs to manually construct the meta-relation set, leading to numerous labor costs. Self-supervised learning (SSL) is treated as a solution to tackle the issue, but still at an early stage for FS-KGR task. Moreover, most of the existing methods ignore leveraging the beneficial information from aliasing relations (AR), i.e., data-rich relations with similar contextual semantics to the target data-poor relation. Therefore, we proposed a novel Self-Supervised Learning model by leveraging Aliasing Relations to assist FS-KGR, termed SARF. Concretely, four main components are designed in our model, i.e., SSL reasoning module, AR-assisted mechanism, fusion module, and scoring function. We first generate the representation of the co-occurrence patterns in a generative manner. Meanwhile, the representations of aliasing relations are learned to enhance reasoning in the AR-assist mechanism. Besides, multiple strategies, i.e., simple summation and learnable fusion, are offered for representation fusion. Finally, the generated representation is used for scoring. Extensive experiments on three few-shot benchmarks demonstrate that SARF achieves state-of-the-art performance compared with other methods in most cases.

Abstract: We propose a second order gradient based method with ADAM and RMSprop for the training of generative adversarial networks. The proposed method is fastest to obtain similar accuracy when compared to prominent second order methods. Unlike state-of-the-art recent methods, it does not require solving a linear system, or it does not require additional mixed second derivative terms. We derive the fixed point iteration corresponding to proposed method, and show that the proposed method is convergent. The proposed method produces better or comparable inception scores, and comparable quality of images compared to other recently proposed state-of-the-art second order methods. Compared to first order methods such as ADAM, it produces significantly better inception scores. The proposed method is compared and validated on popular datasets such as FFHQ, LSUN, CIFAR10, MNIST, and Fashion MNIST for image generation tasks\footnote{Accepted in IJCNN 2023}. Codes: \url{https://github.com/misterpawan/acom}

Abstract: In symbolic regression, the goal is to find an analytical expression that accurately fits experimental data with the minimal use of mathematical symbols such as operators, variables, and constants. However, the combinatorial space of possible expressions can make it challenging for traditional evolutionary algorithms to find the correct expression in a reasonable amount of time. To address this issue, Neural Symbolic Regression (NSR) algorithms have been developed that can quickly identify patterns in the data and generate analytical expressions. However, these methods, in their current form, lack the capability to incorporate user-defined prior knowledge, which is often required in natural sciences and engineering fields. To overcome this limitation, we propose a novel neural symbolic regression method, named Neural Symbolic Regression with Hypothesis (NSRwH) that enables the explicit incorporation of assumptions about the expected structure of the ground-truth expression into the prediction process. Our experiments demonstrate that the proposed conditioned deep learning model outperforms its unconditioned counterparts in terms of accuracy while also providing control over the predicted expression structure.

Abstract: A nuclear reactor based on MIT BEAVRS benchmark was used as a typical power generating Pressurized Water Reactor (PWR). The PARCS v3.2 nodal-diffusion core simulator was used as a full-core reactor physics solver to emulate the operation of a reactor and to generate training, and validation data for the ANN. The ANN was implemented with dedicated Python 3.8 code with Google's TensorFlow 2.0 library. The effort was based to a large extent on the process of appropriate automatic transformation of data generated by PARCS simulator, which was later used in the process of the ANN development. Various methods that allow obtaining better accuracy of the ANN predicted results were studied, such as trying different ANN architectures to find the optimal number of neurons in the hidden layers of the network. Results were later compared with the architectures proposed in the literature. For the selected best architecture predictions were made for different core parameters and their dependence on core loading patterns. In this study, a special focus was put on the prediction of the fuel cycle length for a given core loading pattern, as it can be considered one of the targets for plant economic operation. For instance, the length of a single fuel cycle depending on the initial core loading pattern was predicted with very good accuracy (>99%). This work contributes to the exploration of the usefulness of neural networks in solving nuclear reactor design problems. Thanks to the application of ANN, designers can avoid using an excessive amount of core simulator runs and more rapidly explore the space of possible solutions before performing more detailed design considerations.

Abstract: We propose a model-free reinforcement learning architecture, called distributed attentional actor architecture after conditional attention (DA6-X), to provide better interpretability of conditional coordinated behaviors. The underlying principle involves reusing the saliency vector, which represents the conditional states of the environment, such as the global position of agents. Hence, agents with DA6-X flexibility built into their policy exhibit superior performance by considering the additional information in the conditional states during the decision-making process. The effectiveness of the proposed method was experimentally evaluated by comparing it with conventional methods in an objects collection game. By visualizing the attention weights from DA6-X, we confirmed that agents successfully learn situation-dependent coordinated behaviors by correctly identifying various conditional states, leading to improved interpretability of agents along with superior performance.

Abstract: Graph Neural Networks (GNNs) have shown state-of-the-art improvements in node classification tasks on graphs. While these improvements have been largely demonstrated in a multi-class classification scenario, a more general and realistic scenario in which each node could have multiple labels has so far received little attention. The first challenge in conducting focused studies on multi-label node classification is the limited number of publicly available multi-label graph datasets. Therefore, as our first contribution, we collect and release three real-world biological datasets and develop a multi-label graph generator to generate datasets with tunable properties. While high label similarity (high homophily) is usually attributed to the success of GNNs, we argue that a multi-label scenario does not follow the usual semantics of homophily and heterophily so far defined for a multi-class scenario. As our second contribution, besides defining homophily for the multi-label scenario, we develop a new approach that dynamically fuses the feature and label correlation information to learn label-informed representations. Finally, we perform a large-scale comparative study with $10$ methods and $9$ datasets which also showcase the effectiveness of our approach. We release our benchmark at \url{https://anonymous.4open.science/r/LFLF-5D8C/}.

Abstract: Large language models (LLMs) have made transformed changes for human society. One of the key computation in LLMs is the softmax unit. This operation is important in LLMs because it allows the model to generate a distribution over possible next words or phrases, given a sequence of input words. This distribution is then used to select the most likely next word or phrase, based on the probabilities assigned by the model. The softmax unit plays a crucial role in training LLMs, as it allows the model to learn from the data by adjusting the weights and biases of the neural network. In the area of convex optimization such as using central path method to solve linear programming. The softmax function has been used a crucial tool for controlling the progress and stability of potential function [Cohen, Lee and Song STOC 2019, Brand SODA 2020]. In this work, inspired the softmax unit, we define a softmax regression problem. Formally speaking, given a matrix $A \in \mathbb{R}^{n \times d}$ and a vector $b \in \mathbb{R}^n$, the goal is to use greedy type algorithm to solve \begin{align*} \min_{x} \| \langle \exp(Ax), {\bf 1}_n \rangle^{-1} \exp(Ax) - b \|_2^2. \end{align*} In certain sense, our provable convergence result provides theoretical support for why we can use greedy algorithm to train softmax function in practice.

Abstract: Randomized smoothing (RS) is a well known certified defense against adversarial attacks, which creates a smoothed classifier by predicting the most likely class under random noise perturbations of inputs during inference. While initial work focused on robustness to $\ell_2$ norm perturbations using noise sampled from a Gaussian distribution, subsequent works have shown that different noise distributions can result in robustness to other $\ell_p$ norm bounds as well. In general, a specific noise distribution is optimal for defending against a given $\ell_p$ norm based attack. In this work, we aim to improve the certified adversarial robustness against multiple perturbation bounds simultaneously. Towards this, we firstly present a novel \textit{certification scheme}, that effectively combines the certificates obtained using different noise distributions to obtain optimal results against multiple perturbation bounds. We further propose a novel \textit{training noise distribution} along with a \textit{regularized training scheme} to improve the certification within both $\ell_1$ and $\ell_2$ perturbation norms simultaneously. Contrary to prior works, we compare the certified robustness of different training algorithms across the same natural (clean) accuracy, rather than across fixed noise levels used for training and certification. We also empirically invalidate the argument that training and certifying the classifier with the same amount of noise gives the best results. The proposed approach achieves improvements on the ACR (Average Certified Radius) metric across both $\ell_1$ and $\ell_2$ perturbation bounds.

Abstract: In our work, we propose a novel yet simple approach to obtain an adaptive learning rate for gradient-based descent methods on classification tasks. Instead of the traditional approach of selecting adaptive learning rates via the decayed expectation of gradient-based terms, we use the angle between the current gradient and the new gradient: this new gradient is computed from the direction orthogonal to the current gradient, which further helps us in determining a better adaptive learning rate based on angle history, thereby, leading to relatively better accuracy compared to the existing state-of-the-art optimizers. On a wide variety of benchmark datasets with prominent image classification architectures such as ResNet, DenseNet, EfficientNet, and VGG, we find that our method leads to the highest accuracy in most of the datasets. Moreover, we prove that our method is convergent.

Abstract: Deep reinforcement learning algorithms that learn policies by trial-and-error must learn from limited amounts of data collected by actively interacting with the environment. While many prior works have shown that proper regularization techniques are crucial for enabling data-efficient RL, a general understanding of the bottlenecks in data-efficient RL has remained unclear. Consequently, it has been difficult to devise a universal technique that works well across all domains. In this paper, we attempt to understand the primary bottleneck in sample-efficient deep RL by examining several potential hypotheses such as non-stationarity, excessive action distribution shift, and overfitting. We perform thorough empirical analysis on state-based DeepMind control suite (DMC) tasks in a controlled and systematic way to show that high temporal-difference (TD) error on the validation set of transitions is the main culprit that severely affects the performance of deep RL algorithms, and prior methods that lead to good performance do in fact, control the validation TD error to be low. This observation gives us a robust principle for making deep RL efficient: we can hill-climb on the validation TD error by utilizing any form of regularization techniques from supervised learning. We show that a simple online model selection method that targets the validation TD error is effective across state-based DMC and Gym tasks.

Abstract: The dual use of machine learning applications, where models can be used for both beneficial and malicious purposes, presents a significant challenge. This has recently become a particular concern in chemistry, where chemical datasets containing sensitive labels (e.g. toxicological information) could be used to develop predictive models that identify novel toxins or chemical warfare agents. To mitigate dual use risks, we propose a model-agnostic method of selectively noising datasets while preserving the utility of the data for training deep neural networks in a beneficial region. We evaluate the effectiveness of the proposed method across least squares, a multilayer perceptron, and a graph neural network. Our findings show selectively noised datasets can induce model variance and bias in predictions for sensitive labels with control, suggesting the safe sharing of datasets containing sensitive information is feasible. We also find omitting sensitive data often increases model variance sufficiently to mitigate dual use. This work is proposed as a foundation for future research on enabling more secure and collaborative data sharing practices and safer machine learning applications in chemistry.

Abstract: Opioid and substance misuse is rampant in the United States today, with the phenomenon known as the "opioid crisis". The relationship between substance use and mental health has been extensively studied, with one possible relationship being: substance misuse causes poor mental health. However, the lack of evidence on the relationship has resulted in opioids being largely inaccessible through legal means. This study analyzes the substance use posts on social media with opioids being sold through crypto market listings. We use the Drug Abuse Ontology, state-of-the-art deep learning, and knowledge-aware BERT-based models to generate sentiment and emotion for the social media posts to understand users' perceptions on social media by investigating questions such as: which synthetic opioids people are optimistic, neutral, or negative about? or what kind of drugs induced fear and sorrow? or what kind of drugs people love or are thankful about? or which drugs people think negatively about? or which opioids cause little to no sentimental reaction. We discuss how we crawled crypto market data and its use in extracting posts for fentanyl, fentanyl analogs, and other novel synthetic opioids. We also perform topic analysis associated with the generated sentiments and emotions to understand which topics correlate with people's responses to various drugs. Additionally, we analyze time-aware neural models built on these features while considering historical sentiment and emotional activity of posts related to a drug. The most effective model performs well (statistically significant) with (macroF1=82.12, recall =83.58) to identify substance use disorder.

Abstract: We consider the well-studied problem of learning a linear combination of $k$ ReLU activations with respect to a Gaussian distribution on inputs in $d$ dimensions. We give the first polynomial-time algorithm that succeeds whenever $k$ is a constant. All prior polynomial-time learners require additional assumptions on the network, such as positive combining coefficients or the matrix of hidden weight vectors being well-conditioned. Our approach is based on analyzing random contractions of higher-order moment tensors. We use a multi-scale analysis to argue that sufficiently close neurons can be collapsed together, sidestepping the conditioning issues present in prior work. This allows us to design an iterative procedure to discover individual neurons.

Abstract: Deep neural networks (DNNs) have received tremendous attention and achieved great success in various applications, such as image and video analysis, natural language processing, recommendation systems, and drug discovery. However, inherent uncertainties derived from different root causes have been realized as serious hurdles for DNNs to find robust and trustworthy solutions for real-world problems. A lack of consideration of such uncertainties may lead to unnecessary risk. For example, a self-driving autonomous car can misdetect a human on the road. A deep learning-based medical assistant may misdiagnose cancer as a benign tumor. In this work, we study how to measure different uncertainty causes for DNNs and use them to solve diverse decision-making problems more effectively. In the first part of this thesis, we develop a general learning framework to quantify multiple types of uncertainties caused by different root causes, such as vacuity (i.e., uncertainty due to a lack of evidence) and dissonance (i.e., uncertainty due to conflicting evidence), for graph neural networks. We provide a theoretical analysis of the relationships between different uncertainty types. We further demonstrate that dissonance is most effective for misclassification detection and vacuity is most effective for Out-of-Distribution (OOD) detection. In the second part of the thesis, we study the significant impact of OOD objects on semi-supervised learning (SSL) for DNNs and develop a novel framework to improve the robustness of existing SSL algorithms against OODs. In the last part of the thesis, we create a general learning framework to quantity multiple uncertainty types for multi-label temporal neural networks. We further develop novel uncertainty fusion operators to quantify the fused uncertainty of a subsequence for early event detection.