相关论文: Hypernym Detection Using Strict Partial Order Netw…

Neural networks are fundamental tools of modern machine learning. The standard paradigm assumes binary interactions (across feedforward linear passes) between inter-tangled units, organized in sequential layers. Generalized architectures…

The robustness and anomaly detection capability of neural networks are crucial topics for their safe adoption in the real-world. Moreover, the over-parameterization of recent networks comes with high computational costs and raises questions…

Activation sparsity offers a compelling route to accelerate large language model (LLM) inference by selectively suppressing hidden activations, yet existing approaches exhibit severe accuracy degradation at high sparsity. We show that this…

Learning complex dynamics driven by partial differential equations directly from data holds great promise for fast and accurate simulations of complex physical systems. In most cases, this problem can be formulated as an operator learning…

Recognizing actions from still images is popularly studied recently. In this paper, we model an action class as a flexible number of spatial configurations of body parts by proposing a new spatial SPN (Sum-Product Networks). First, we…

Recent advances to combine structured regression models and deep neural networks for better interpretability, more expressiveness, and statistically valid uncertainty quantification demonstrate the versatility of semi-structured neural…

We consider the problem of \textit{true} open-world semi-supervised node classification, in which nodes in a graph either belong to known or new classes, with the latter not present during training. Existing methods detect and reject new…

We introduce semi-parametric inducing point networks (SPIN), a general-purpose architecture that can query the training set at inference time in a compute-efficient manner. Semi-parametric architectures are typically more compact than…

Weakly supervised object localization remains challenging, where only image labels instead of bounding boxes are available during training. Object proposal is an effective component in localization, but often computationally expensive and…

In previous work, we pointed out the limitations of standard Bayesian networks as a modeling framework for large, complex domains. We proposed a new, richly structured modeling language, {em Object-oriented Bayesian Netorks}, that we argued…

Conventional training of deep neural networks requires a large number of the annotated image which is a laborious and time-consuming task, particularly for rare objects. Few-shot object detection (FSOD) methods offer a remedy by realizing…

Approximate variational inference has shown to be a powerful tool for modeling unknown complex probability distributions. Recent advances in the field allow us to learn probabilistic models of sequences that actively exploit spatial and…

In recent years, deep learning technology has been maturely applied in the field of object detection, and most algorithms tend to be supervised learning. However, a large amount of labeled data requires high costs of human resources, which…

We introduce a novel framework for uncertainty quantification of solution operators associated with stochastic partial differential equations (SPDEs). Although SPDEs play a central role in modeling complex physical systems under…

Distinguishing lexical relations has been a long term pursuit in natural language processing (NLP) domain. Recently, in order to detect lexical relations like hypernymy, meronymy, co-hyponymy etc., distributional semantic models are being…

Weakly supervised text classification methods typically train a deep neural classifier based on pseudo-labels. The quality of pseudo-labels is crucial to final performance but they are inevitably noisy due to their heuristic nature, so…

Semi-supervised semantic segmentation (SSS) is an important task that utilizes both labeled and unlabeled data to reduce expenses on labeling training examples. However, the effectiveness of SSS algorithms is limited by the difficulty of…

We present the Supervised Directional Similarity Network (SDSN), a novel neural architecture for learning task-specific transformation functions on top of general-purpose word embeddings. Relying on only a limited amount of supervision from…

We investigate the supervised machine learning of few interacting bosons in optical speckle disorder via artificial neural networks. The learning curve shows an approximately universal power-law scaling for different particle numbers and…

We introduce a new unsupervised anomaly detection ensemble called SPI which can harness privileged information - data available only for training examples but not for (future) test examples. Our ideas build on the Learning Using Privileged…