In this paper, we propose a framework that unifies sequence- and graph-based methods as energy-based models (EBMs) with different energy functions.
From the stored propagated features, we propose to learn multi-scale temporal contexts, and re-fill the learned temporal contexts into the modules of our compression scheme, including the contextual encoder-decoder, the frame generator, and the temporal context encoder.
This paper studies a distributed policy gradient in collaborative multi-agent reinforcement learning (MARL), where agents over a communication network aim to find the optimal policy to maximize the average of all agents' local returns.
Last, to enhance the embedding space learning, an additional pixel-wise metric learning module is devised with triplet loss formulated on the pixel-level embedding of the input image.
Kohn-Sham regularizer (KSR) is a machine learning approach that optimizes a physics-informed exchange-correlation functional within a differentiable Kohn-Sham density functional theory framework.
Github Copilot, trained on billions of lines of public code, has recently become the buzzword in the computer science research and practice community.
However, this nature was seldom considered in previous studies on image compression, which usually chose one possible image as reconstruction, e. g. the one with the maximal a posteriori probability.
With the rapid development of whole brain imaging technology, a large number of brain images have been produced, which puts forward a great demand for efficient brain image compression methods.
Given the success of reinforcement learning (RL) in various domains, it is promising to explore the application of its methods to the development of intelligent and autonomous cyber agents.
Graph neural networks (GNNs), which learn the node representations by recursively aggregating information from its neighbors, have become a predominant computational tool in many domains.
Code representation learning, which aims to encode the semantics of source code into distributed vectors, plays an important role in recent deep-learning-based models for code intelligence.
In this work, we propose a novel framework for density forecast combination by constructing time-varying weights based on time series features, which is called Feature-based Bayesian Forecasting Model Averaging (FEBAMA).
It is generally believed that a translation memory (TM) should be beneficial for machine translation tasks.
To this end, we analyze the bottleneck of deep GNNs by leveraging the Dirichlet energy of node embeddings, and propose a generalizable principle to guide the training of deep GNNs.
To learn with noisy clients, we propose a simple yet effective FL framework, named Federated Noisy Client Learning (Fed-NCL), which is a plug-and-play algorithm and contains two main components: a data quality measurement (DQM) to dynamically quantify the data quality of each participating client, and a noise robust aggregation (NRA) to adaptively aggregate the local models of each client by jointly considering the amount of local training data and the data quality of each client.
Due to the growing awareness of driving safety and the development of sophisticated technologies, advanced driving assistance system (ADAS) has been equipped in more and more vehicles with higher accuracy and lower price.
For existing old ads, GMEs first build a graph to connect them with new ads, and then adaptively distill useful information.
As a promising tool to better understand the learning dynamic of minibatch SGD, the information bottleneck (IB) theory claims that the optimization process consists of an initial fitting phase and the following compression phase.
In addition to aligning the global distribution, the real domain adaptation should also align the meso distribution and the micro distribution.
Recently, adversarial attack methods have been developed to challenge the robustness of machine learning models.
Asynchronous FL has a natural advantage in mitigating the straggler effect, but there are threats of model quality degradation and server crash.
In our framework, the server evaluates devices' value of training based on their training loss.
no code implementations • 7 Apr 2021 • Vivek Singh Bawa, Gurkirt Singh, Francis KapingA, Inna Skarga-Bandurova, Elettra Oleari, Alice Leporini, Carmela Landolfo, Pengfei Zhao, Xi Xiang, Gongning Luo, Kuanquan Wang, Liangzhi Li, Bowen Wang, Shang Zhao, Li Li, Armando Stabile, Francesco Setti, Riccardo Muradore, Fabio Cuzzolin
For an autonomous robotic system, monitoring surgeon actions and assisting the main surgeon during a procedure can be very challenging.
The key procedure of haze image translation through adversarial training lies in the disentanglement between the feature only involved in haze synthesis, i. e. style feature, and the feature representing the invariant semantic content, i. e. content feature.
In this paper, we conducted a systematic literature review to search and analyze how deep learning approaches have been applied in the context of malware defenses in the Android environment.
Distributed quantum metrology can enhance the sensitivity for sensing spatially distributed parameters beyond the classical limits.
To address the conflict between learning SLO and energy efficiency, we propose DEAL, an energy efficient learning system that saves energy and preserves privacy with a decremental learning design.
As a potential development direction of future transportation, the vacuum tube ultra-high-speed train (UHST) wireless communication systems have newly different channel characteristics from existing high-speed train (HST) scenarios.
To improve adaptation efficiency, we learn to recover the user policy and reward from only a few interactions via an inverse reinforcement learning method to assist a meta-level recommendation agent.
Given a quantum circuit, a quantum computer can sample the output distribution exponentially faster in the number of bits than classical computers.
Including prior knowledge is important for effective machine learning models in physics, and is usually achieved by explicitly adding loss terms or constraints on model architectures.
Different from previous work, in our model, factor discovery and representation learning are simultaneously conducted, and we are able to handle extra attribute information and knowledge.
This paper presents a DNN bottleneck reinforcement scheme to alleviate the vulnerability of Deep Neural Networks (DNN) against adversarial attacks.
Retrosynthesis -- the process of identifying a set of reactants to synthesize a target molecule -- is of vital importance to material design and drug discovery.
In this work, we propose a technique for combining gradient-based methods with symbolic techniques to scale such analyses and demonstrate its application for model explanation.
To overcome this complexity, we employ an online minimum drift plus penalty (MDPP) approach for SAEV systems that (i) does not require a priori knowledge of customer arrival rates to the different parts of the system (i. e. it is practical from a real-world deployment perspective), (ii) ensures the stability of customer waiting times, (iii) ensures that the deviation of dispatch costs from a desirable dispatch cost can be controlled, and (iv) has a computational time-complexity that allows for real-time implementation.
Autoencoders have been widely used for dimensional reduction and feature extraction.
Low-cost passive intelligent reflecting surfaces (IRSs) have recently been envisioned as a revolutionary technology capable of reconfiguring the wireless propagation environment through carefully tuning reflection elements.
1 code implementation • 31 May 2020 • Hong Yu, Li Li, Hsin-hui Huang, Yang Wang, Yingtong Liu, Edison Ong, Anthony Huffman, Tao Zeng, Jingsong Zhang, Pengpai Li, Zhiping Liu, Xiangyan Zhang, Xianwei Ye, Samuel K. Handelman, Gerry Higgins, Gilbert S. Omenn, Brian Athey, Junguk Hur, Luonan Chen, Yongqun He
We hypothesized that ontology can be used as an integrative platform to classify and analyze HCI and disease outcomes.
Other Quantitative Biology
The quantum approximate optimization algorithm (QAOA) is widely seen as a possible usage of noisy intermediate-scale quantum (NISQ) devices.
We show the feasibility of training with mobile CPUs, where training 100 epochs takes less than 10 mins and can be boosted 3-5 times with feature transfer.
Device fingerprints like sensor pattern noise (SPN) are widely used for provenance analysis and image authentication.
In this paper, (to the best of our knowledge) we provide the first attempt to leverage the data augmentation technique to improve the performance of multi-label learning.
With the explosive growth of online products and content, recommendation techniques have been considered as an effective tool to overcome information overload, improve user experience, and boost business revenue.
no code implementations • 13 Jan 2020 • Harrison Ball, Michael J. Biercuk, Andre Carvalho, Jiayin Chen, Michael Hush, Leonardo A. De Castro, Li Li, Per J. Liebermann, Harry J. Slatyer, Claire Edmunds, Virginia Frey, Cornelius Hempel, Alistair Milne
Manipulating quantum computing hardware in the presence of imperfect devices and control systems is a central challenge in realizing useful quantum computers.
In this paper, we propose the Topic-coherent Hierarchical Recurrent Encoder-Decoder model (THRED) to diversify the generated responses without deviating the contextual topics for multi-turn conversations.
The block-based coding structure in the hybrid video coding framework inevitably introduces compression artifacts such as blocking, ringing, etc.
Both offline and online experiments demonstrate the effectiveness of MA-DNN for practical CTR prediction services.
In this paper, we study how to learn an appropriate lane changing strategy for autonomous vehicles by using deep reinforcement learning.
The intuitions are that ads shown together may influence each other, clicked ads reflect a user's preferences, and unclicked ads may indicate what a user dislikes to certain extent.
Ranked #1 on Click-Through Rate Prediction on Avito
We present RL-VAE, a graph-to-graph variational autoencoder that uses reinforcement learning to decode molecular graphs from latent embeddings.
Machine learning, especially deep neural networks, has been rapidly developed in fields including computer vision, speech recognition and reinforcement learning.
The second part, which we call Neural-Guided Monte Carlo Tree Search, uses the network during a search to find an expression that conforms to a set of data points and desired leading powers.
While MVAE is notable in its impressive source separation performance, the convergence-guaranteed optimization algorithm and that it allows us to estimate source-class labels simultaneously with source separation, there are still two major drawbacks, i. e., the high computational complexity and unsatisfactory source classification accuracy.
Repackaging is a serious threat to the Android ecosystem as it deprives app developers of their benefits, contributes to spreading malware on users' devices, and increases the workload of market maintainers.
Up to the present, it still lacks a comprehensive study on how current diverse DL frameworks and platforms influence the DL software development process.
We present a framework, which we call Molecule Deep $Q$-Networks (MolDQN), for molecule optimization by combining domain knowledge of chemistry and state-of-the-art reinforcement learning techniques (double $Q$-learning and randomized value functions).
Ranked #1 on Molecular Graph Generation on ZINC (QED Top-3 metric)
This paper deals with a multichannel audio source separation problem under underdetermined conditions.
In this paper, geometric and photometric constraints are combined to improve the alignment quality, which is based on the observation that these two kinds of constraints are complementary.
This paper proposes a multichannel source separation technique called the multichannel variational autoencoder (MVAE) method, which uses a conditional VAE (CVAE) to model and estimate the power spectrograms of the sources in a mixture.
To do this, by sharing the same spirit of mutation testing in traditional software, we first define a set of source-level mutation operators to inject faults to the source of DL (i. e., training data and training programs).
Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data.
We introduce tensor field neural networks, which are locally equivariant to 3D rotations, translations, and permutations of points at every layer.
Topological data analysis offers a robust way to extract useful information from noisy, unstructured data by identifying its underlying structure.
no code implementations • 13 Jan 2018 • Sheng-Kai Liao, Wen-Qi Cai, Johannes Handsteiner, Bo Liu, Juan Yin, Liang Zhang, Dominik Rauch, Matthias Fink, Ji-Gang Ren, Wei-Yue Liu, Yang Li, Qi Shen, Yuan Cao, Feng-Zhi Li, Jian-Feng Wang, Yong-Mei Huang, Lei Deng, Tao Xi, Lu Ma, Tai Hu, Li Li, Nai-Le Liu, Franz Koidl, Peiyuan Wang, Yu-Ao Chen, Xiang-Bin Wang, Michael Steindorfer, Georg Kirchner, Chao-Yang Lu, Rong Shu, Rupert Ursin, Thomas Scheidl, Cheng-Zhi Peng, Jian-Yu Wang, Anton Zeilinger, Jian-Wei Pan
This was on the one hand the transmission of images in a one-time pad configuration from China to Austria as well as from Austria to China.
While these models commonly use features extracted from the structure of PE files, we propose that icons from these files can also help better predict malware.
Stochastic principal component analysis (SPCA) has become a popular dimensionality reduction strategy for large, high-dimensional datasets.
Detrending based methods decompose original flow series into trend and residual series, in which trend describes the fixed temporal pattern in traffic flow and residual series is used for prediction.
We develop a novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network.
A block can be down-sampled before being compressed by normal intra coding, and then up-sampled to its original resolution.
This paper proposes a novel advanced motion model to handle the irregular motion for the cubic map projection of 360-degree video.
Determining the optimal size and orientation of small-scale residential based PV arrays will become increasingly complex in the future smart grid environment with the introduction of smart meters and dynamic tariffs.
Last year, at least 30, 000 scientific papers used the Kohn-Sham scheme of density functional theory to solve electronic structure problems in a wide variety of scientific fields, ranging from materials science to biochemistry to astrophysics.
One single code change can significantly influence a wide range of software systems and their users.
To the best of our knowledge, we are the first to tackle the imbalance problem in multi-label classification with many labels.
Accurate approximations to density functionals have recently been obtained via machine learning (ML).
Kernel ridge regression is used to approximate the kinetic energy of non-interacting fermions in a one-dimensional box as a functional of their density.