Traffic engineering (TE) has attracted extensive attention over the years. Operators expect to design a TE scheme that accommodates traffic dynamics well and achieves good TE performance with little overhead. Some approaches like oblivious routing compute an optimal static routing based on a large traffic matrix (TM) range, which usually leads to much performance loss. Many approaches compute routing solutions based on one or a few representative TMs obtained from observed historical TMs. However, they may suffer from performance degradation for unexpected TMs and usually induce much overhead of system operating. In this paper, we propose ALTE, an adaptive and low-cost TE scheme based on TM classification. We develop a novel clustering algorithm to properly group a set of historical TMs into several clusters and compute a candidate routing solution for each TM cluster. A machine learning classifier is trained to infer the proper candidate routing solution online based on the features extracted from some easily measured statistics. We implement a system prototype of ALTE and do extensive simulations and experiments using both real and synthetic traffic traces. The results show that ALTE achieves near-optimal performance for dynamic traffic and introduces little overhead of routing updates.

Floods are one of the most frequent and disastrous natural hazards that affect millions of people and cause damage all around the world. Satellite-based flood mapping using optical or synthetic aperture radar (SAR) data has become an important component of disaster response. For extreme event monitoring such as floods, SAR and optical data have obvious complementary advantages in terms of data availability and information richness, thereby the combined use of the two data for flood monitoring has great application potential. However, there is a lack of efficient processing methods for both SAR and optical data, which limits the cross-application of these two complementary data in flood monitoring. In this study, we develop an unconditional image thresholding approach of optical and SAR data (UIT) to monitor large-scale floods. The UIT algorithm constructs a variable Gaussian mixture model with parameter prior to express the probability distribution of water and non-water pixels, which can be effectively compatible with optical and SAR data. To reduce the omission error of the flood extent, spatial context information and dual-polarization information are exploited for fast flood detection. The experiment used Sentinel-1 SAR data and Sentinel-2 optical data to monitor two severe flooding events in the history of the Gulf of Mexico. Compared with several state-of-the-art methods, the proposed algorithm can distinguish water from non-water pixels with higher accuracy (more than 5% improvement in OA).

Rapid and accurate monitoring of surface water is critical for water resource management, environmental protection, sustainable urban development, among other issues. Traditional threshold-based or classification-based surface water mapping methods often require adjusting thresholds or training samples for different regions or different sensors, which may hinder the generalization performance of the method in large-scale water body mapping. We propose an unsupervised deep learning water body mapping framework (UUCP) for unlabeled large-scale optical remote sensing images in this study. The UUCP framework adopts an unsupervised multi-segment thresholding strategy to achieve the transition from label-free learning to noisy label learning, and learns robust multi-scale features of water bodies by the developed channel attention multi-scale surface water extraction network and training strategies under noise labels. The results show that our proposed method performs well in the overall performance of water extraction and is applicable to different sensors.

Robust network design, which aims to guarantee network availability under various failure scenarios while optimizing performance/cost objectives, has received significant attention. Existing approaches often rely on model-based mixed-integer optimization that is hard to scale or employ deep learning to solve specific engineering problems yet with limited generalizability. In this paper, we show that failure evaluation provides a common kernel to improve the tractability and scalability of existing solutions. By providing a neural network function approximation of this common kernel using graph attention networks, we develop a unified learning-based framework, FERN, for scalable Failure Evaluation and Robust Network design. FERN represents rich problem inputs as a graph and captures both local and global views by attentively performing feature extraction from the graph. It enables a broad range of robust network design problems, including robust network validation, network upgrade optimization, and fault-tolerant traffic engineering that are discussed in this paper, to be recasted with respect to the common kernel and thus computed efficiently using neural networks and over a small set of critical failure scenarios. Extensive experiments on real-world network topologies show that FERN can efficiently and accurately identify key failure scenarios for both OSPF and optimal routing scheme, and generalizes well to different topologies and input traffic patterns. It can speed up multiple robust network design problems by more than 80x, 200x, 10x, respectively with negligible performance gap.

IPv6 has shown notable growth in recent years, imposing the need for high-speed IPv6 lookup. As the forwarding rate of virtual switches continues increasing, software-based IPv6 lookup without using special hardware such as TCAM, GPU, and FPGA is of academic interest and industrial importance. Existing studies achieve fast software IPv4 lookup by reducing the operation number, as well as reducing the memory footprint to benefit from CPU cache. However, in the situation of 128-bit IPv6 addresses, it is challenging to keep both operation numbers and memory footprints small. To address the issue, we propose the Neurotrie data structure, which supports fast lookup and arbitrary strides. Thus, a good balance can be made between trie depth and memory footprint by computing the proper stride for each Neurotrie node. We model the optimal Neurotrie problem which minimizes the depth with limited memory footprint and develop a pseudo-polynomial time baseline algorithm to construct Neurotrie using dynamic programming. To improve the performance and reduce the computation complexity, we develop a deep reinforcement learning-based approach, which leverages a deep neural network to construct Neurotrie efficiently, based on characteristics captured from real IPv6 prefixes. We further refine the data structure called Neurotrie-S and develop an efficient mechanism for routing updates. Experiments on real routing tables show that Neurotrie-S achieves a lookup rate 34% higher than that of state-of-the-art approaches. We implement a Neurotrie-based software switch, and the forwarding rate of Neurotrie-S is about 10% to 345% higher than other algorithms.

The point pair feature (PPF) is widely used for 6D pose estimation. In this paper, we propose an efficient 6D pose estimation method based on the PPF framework. We introduce a well-targeted down-sampling strategy that focuses on edge areas for efficient feature extraction for complex geometry. A pose hypothesis validation approach is proposed to resolve ambiguity due to symmetry by calculating the edge matching degree. We perform evaluations on two challenging datasets and one real-world collected dataset, demonstrating the superiority of our method for pose estimation for geometrically complex, occluded, symmetrical objects. We further validate our method by applying it to simulated punctures.

Emerging applications raise critical QoS requirements for the Internet. The improvements in flow classification technologies, software-defined networks (SDN), and programmable network devices make it possible to fast identify users’ requirements and control the routing for fine-grained traffic flows. Meanwhile, the problem of optimizing the forwarding paths for traffic flows with multiple QoS requirements in an online fashion is not addressed sufficiently. To address the problem, we propose DRL-OR-S, a highly scalable online routing algorithm using multi-agent deep reinforcement learning. DRL-OR-S adopts a comprehensive reward function, an efficient learning algorithm, and a novel deep neural network structure to learn appropriate routing strategies for different types of flow requirements. In order to enhance the generalization and scalability, we propose a novel graph-based actor-critic network architecture and a carefully designed input state for DRL-OR-S. To accelerate the training process and guarantee reliability, we further introduce an NN-simulator for efficient offline training and a safe learning mechanism to avoid unsafe routes during the online routing process. We implement DRL-OR-S under SDN architecture and conduct Mininet-based experiments using real network topologies and traffic traces. The results validate that DRL-OR-S can well satisfy the requirements of latency-sensitive, throughput-sensitive, latency-throughput-sensitive, and latency-loss-sensitive flows at the same time, while exhibiting great adaptiveness and reliability under the scenarios of link failure, traffic change, unseen large topology and partial deployment.

IPv6 has shown notable growth in recent years, imposing the need for high-speed IPv6 lookup. As the forwarding rate of virtual switches continues increasing, software-based IPv6 lookup without using special hardware such as TCAM, GPU, and FPGA is of academic interest and industrial importance. Existing studies achieve fast software IPv4 lookup by reducing the operation number, as well as reducing the memory footprint so as to benefit from CPU cache. However, in the situation of 128-bit IPv6 addresses, it is challenging to keep both operation numbers and memory footprints small. To address the issue, we propose the Neurotrie data structure, which supports fast lookup and arbitrary strides. Thus, a good balance can be made between trie depth and memory footprint by computing the proper stride for each Neurotrie node. We model the optimal Neurotrie problem which minimizes the depth with limited memory footprint and develop a pseudo-polynomial time baseline algorithm to construct Neurotrie using dynamic programming. To improve the performance and reduce the computation complexity, we develop a deep reinforcement learning-based approach, which leverages a deep neural network to construct Neurotrie efficiently, based on characteristics captured from real IPv6 prefixes. We further refine the data structure and develop an efficient mechanism for routing updates. Experiments on real routing tables show that Neurotrie achieves a lookup rate 34% higher than that of state-of-the-art approaches.

Relation contexts have been proved to be useful for many challenging vision tasks. In the field of 3D object detection, previous methods have been taking the advantage of context encoding, graph embedding, or explicit relation reasoning to extract relation contexts. However, there exist inevitably redundant relation contexts due to noisy or low-quality proposals. In fact, invalid relation contexts usually indicate underlying scene misunderstanding and ambiguity, which may, on the contrary, reduce the performance in complex scenes. Inspired by recent attention mechanism like Transformer, we propose a novel 3D attention-based relation module (ARM3D). It encompasses object-aware relation reasoning to extract pair-wise relation contexts among qualified proposals and an attention module to distribute attention weights towards different relation contexts. In this way, ARM3D can take full advantage of the useful relation contexts and filter those less relevant or even confusing contexts, which mitigates the ambiguity in detection. We have evaluated the effectiveness of ARM3D by plugging it into several state-of-the-art 3D object detectors and showing more accurate and robust detection results. Extensive experiments show the capability and generalization of ARM3D on 3D object detection. Our source code is available at https://github.com/lanlan96/ARM3D .

Emerging applications raise critical QoS requirements for the Internet. The improvements of flow classification technologies, software defined networks (SDN), and programmable network devices make it possible to fast identify users' requirements and control the routing for fine-grained traffic flows. Meanwhile, the problem of optimizing the forwarding paths for traffic flows with multiple QoS requirements in an online fashion is not addressed sufficiently. To address the problem, we propose DRL-OR, an online routing algorithm using multi-agent deep reinforcement learning. DRL-OR organizes the agents to generate routes in a hop-by-hop manner, which inherently has good scalability. It adopts a comprehensive reward function, an efficient learning algorithm, and a novel deep neural network structure to learn an appropriate routing policy for different types of flow requirements. To guarantee the reliability and accelerate the online learning process, we further introduce safe learning mechanism to DRL-OR. We implement DRL-OR under SDN architecture and conduct Mininet-based experiments by using real network topologies and traffic traces. The results validate that DRL-OR can well satisfy the requirements of latency-sensitive, throughput-sensitive, latency-throughput-sensitive, and latency-loss-sensitive flows at the same time, while exhibiting great adaptiveness and reliability under the scenarios of link failure, traffic change, and partial deployment.

Lots of studies focus on distributed traffic engineering (TE) where routers make routing decisions independently. Existing approaches usually tackle distributed TE problems through traditional optimization methods. However, due to the intrinsic complexity of the distributed TE problems, routing decisions cannot be obtained efficiently, which leads to significant performance degradation, especially for highly dynamic traffic. Emerging machine learning technologies like deep reinforcement learning (DRL) provide a new choice to address TE problems in an experience-driven method. In this paper, we propose DATE, a distributed and adaptive TE framework with DRL. DATE distributes well-trained agents to the routers in the located network. Each agent makes local routing decisions independently based on link utilization ratios flooded by each router periodically. To coordinate the distributed agents to achieve the global optimization in different traffic conditions, we construct candidate paths, develop the agents carefully, and realize a virtual environment to train the agents with a DRL algorithm. We do extensive simulations and experiments using real-world network topologies with both real and synthetic traffic traces. The results show that DATE outperforms some existing approaches and yields near-optimal performance with superior robustness.

Traffic engineering (TE) attracts extensive researches over the years. Operators expect to design a TE scheme which accommodates traffic dynamics well and achieves good TE performance with little overhead. Some approaches like oblivious routing compute an optimal static routing based on a large traffic matrix (TM) range, which usually leads to much performance loss. Many approaches compute routings based on one or a few representative TMs obtained from observed historical TMs. However, they may suffer performance degradation for unexpected TMs and usually induce much overhead of system operating. In this paper, we propose ALTE, an adaptive and low-cost TE scheme based on TM classification. We develop a novel clustering algorithm to properly group a set of historical TMs into several clusters and compute a candidate routing for each TM cluster. A machine learning classifier is trained to infer the proper candidate routing online based on the features extracted from some easily measured statistics. We implement a system prototype of ALTE and do extensive simulations and experiments using both real and synthetic traffic traces. The results show that ALTE achieves near-optimal performance for dynamic traffic and introduces small overhead of routing updates.

Asking good questions in large-scale, open-domain conversational systems is quite significant yet rather untouched.This task, substantially different from traditional question generation, requires to question not only with various patterns but also on diverse and relevant topics.We observe that a good question is a natural composition of interrogatives, topic words, and ordinary words.Interrogatives lexicalize the pattern of questioning, topic words address the key information for topic transition in dialogue, and ordinary words play syntactical and grammatical roles in making a natural sentence.We devise two typed decoders (soft typed decoder and hard typed decoder) in which a type distribution over the three types is estimated and used to modulate the final generation distribution.Extensive experiments show that the typed decoders outperform state-of-the-art baselines and can generate more meaningful questions.

Mineral dust aerosols can influence the Earth's climate system to a significant degree and have a strong effect on terrestrial and oceanic biogeochemical cycles. As one step in quantifying dust sources, sinks, and transport, this paper seeks to quantify the presence of dust storms in the Sahara desert, which is the most active worldwide source of dust. Our work is based on the SEVIRI infrared imager on-board the geostationary Meteosat-8 satellite, providing three separate channels at a 3km by 3km resolution. The significant challenge is that the infrared channels are highly influenced by the presence of water clouds and surface temperatures, which complicate the identification of dust-cloud anomalies. This paper develops a method of spatio-temporal background estimation from sparse data as a way of recovering dust images and presents results on real data.