The exponential growth in scholarly publications necessitates advanced tools for efficient article retrieval, especially in interdisciplinary fields where diverse terminologies are used to describe similar research.
To address the gradient mismatch problem in STE, we further consider the quantized errors and its second-order derivatives for better stability.
Imbalanced datasets are commonly observed in various real-world applications, presenting significant challenges in training classifiers.
Those studies face challenges, either in inaccurate predictions of sensitive attributes or the need to mitigate unequal distribution of manually defined non-sensitive attributes related to bias.
We formulate context sampling into the Markov decision process and exploit deep reinforcement learning to optimize the time series domain adaptation process via context sampling and design a tailored reward function to generate domain-invariant features that better align two domains for anomaly detection.
The role of data in building AI systems has recently been significantly magnified by the emerging concept of data-centric AI (DCAI), which advocates a fundamental shift from model advancements to ensuring data quality and reliability.
Knowledge graph data are prevalent in real-world applications, and knowledge graph neural networks (KGNNs) are essential techniques for knowledge graph representation learning.
Although prior work has explored learning-based approaches for the device placement of computational graphs, embedding table placement remains to be a challenging problem because of 1) the operation fusion of embedding tables, and 2) the generalizability requirement on unseen placement tasks with different numbers of tables and/or devices.
Motivated by this, we investigate developing a learning-based over-sampling algorithm to optimize the classification performance, which is a challenging task because of the huge and hierarchical decision space.
Prior work has approached TSC from two major directions: (1) similarity-based methods that classify time-series based on the nearest neighbors, and (2) deep learning models that directly learn the representations for classification in a data-driven manner.
1 code implementation • 9 Aug 2021 • Daochen Zha, Zaid Pervaiz Bhat, Yi-Wei Chen, Yicheng Wang, Sirui Ding, Jiaben Chen, Kwei-Herng Lai, Mohammad Qazim Bhat, Anmoll Kumar Jain, Alfredo Costilla Reyes, Na Zou, Xia Hu
Action recognition is an important task for video understanding with broad applications.
Supervised regression to demonstrations has been demonstrated to be a stable way to train deep policy networks.
We present TODS, an automated Time Series Outlier Detection System for research and industrial applications.
Specifically, existing strategies have been focused on making the top instances more likely to be anomalous based on the feedback.
It is a challenging task to develop an effective aggregation strategy for each node, given complex graphs and sparse features.
In this work, we introduce dual policy distillation(DPD), a student-student framework in which two learners operate on the same environment to explore different perspectives of the environment and extract knowledge from each other to enhance their learning.
The goal of RLCard is to bridge reinforcement learning and imperfect information games, and push forward the research of reinforcement learning in domains with multiple agents, large state and action space, and sparse reward.
Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand.
Image perception is one of the most direct ways to provide contextual information about a user concerning his/her surrounding environment; hence images are a suitable proxy for contextual recommendation.
Cross-domain collaborative filtering (CF) aims to alleviate data sparsity in single-domain CF by leveraging knowledge transferred from related domains.