When facing changing environments in the real world, the lightweight model on client devices suffers from severe performance drops under distribution shifts. The main limitations of the existing device model lie in (1) unable to update due to the computation limit of the device, (2) the limited generalization ability of the lightweight model. Meanwhile, recent large models have shown strong generalization capability on the cloud while they can not be deployed on client devices due to poor computation constraints. To enable the device model to deal with changing environments, we propose a new learning paradigm of Cloud-Device Collaborative Continual Adaptation, which encourages collaboration between cloud and device and improves the generalization of the device model. Based on this paradigm, we further propose an Uncertainty-based Visual Prompt Adapted (U-VPA) teacher-student model to transfer the generalization capability of the large model on the cloud to the device model. Specifically, we first design the Uncertainty Guided Sampling (UGS) to screen out challenging data continuously and transmit the most out-of-distribution samples from the device to the cloud. Then we propose a Visual Prompt Learning Strategy with Uncertainty guided updating (VPLU) to specifically deal with the selected samples with more distribution shifts. We transmit the visual prompts to the device and concatenate them with the incoming data to pull the device testing distribution closer to the cloud training distribution. We conduct extensive experiments on two object detection datasets with continually changing environments. Our proposed U-VPA teacher-student framework outperforms previous state-of-the-art test time adaptation and device-cloud collaboration methods. The code and datasets will be released.
We present a novel methodology for neural network backdoor attacks. Unlike existing training-time attacks where the Trojaned network would respond to the Trojan trigger after training, our approach inserts a Trojan that will remain dormant until it is activated. The activation is realized through a specific perturbation to the network's weight parameters only known to the attacker. Our analysis and the experimental results demonstrate that dormant Trojaned networks can effectively evade detection by state-of-the-art backdoor detection methods.
Arrival/Travel times for public transit exhibit variability on account of factors like seasonality, dwell times at bus stops, traffic signals, travel demand fluctuation etc. The developing world in particular is plagued by additional factors like lack of lane discipline, excess vehicles, diverse modes of transport and so on. This renders the bus arrival time prediction (BATP) to be a challenging problem especially in the developing world. A novel data-driven model based on recurrent neural networks (RNNs) is proposed for BATP (in real-time) in the current work. The model intelligently incorporates both spatial and temporal correlations in a unique (non-linear) fashion distinct from existing approaches. In particular, we propose a Gated Recurrent Unit (GRU) based Encoder-Decoder(ED) OR Seq2Seq RNN model (originally introduced for language translation) for BATP. The geometry of the dynamic real time BATP problem enables a nice fit with the Encoder-Decoder based RNN structure. We feed relevant additional synchronized inputs (from previous trips) at each step of the decoder (a feature classically unexplored in machine translation applications). Further motivated from accurately modelling congestion influences on travel time prediction, we additionally propose to use a bidirectional layer at the decoder (something unexplored in other time-series based ED application contexts). The effectiveness of the proposed algorithms is demonstrated on real field data collected from challenging traffic conditions. Our experiments indicate that the proposed method outperforms diverse existing state-of-art data-driven approaches proposed for the same problem.
Satellite Image Time Series (SITS) of the Earth's surface provide detailed land cover maps, with their quality in the spatial and temporal dimensions consistently improving. These image time series are integral for developing systems that aim to produce accurate, up-to-date land cover maps of the Earth's surface. Applications are wide-ranging, with notable examples including ecosystem mapping, vegetation process monitoring and anthropogenic land-use change tracking. Recently proposed methods for SITS classification have demonstrated respectable merit, but these methods tend to lack native mechanisms that exploit the temporal dimension of the data; commonly resulting in extensive data pre-processing prohibitively long training times. To overcome these shortcomings, this paper seeks to study and enhance the newly proposed method for SITS classification from literature; namely Temporal CNNs. Comprehensive experiments are carried out on two benchmark SITS datasets with the results demonstrating that Temporal CNNs display a superior or competitive performance to the benchmark algorithms for both datasets. Investigations into the Temporal CNNs architecture also highlighted the non-trivial task of optimising the model for a new dataset.
According to multiple authoritative authorities, including the World Health Organization, vision-related impairments and disorders are becoming a significant issue. According to a recent report, one of the leading causes of irreversible blindness in persons over the age of 50 is delayed cataract treatment. A cataract is a cloudy spot in the eye's lens that causes visual loss. Cataracts often develop slowly and consequently result in difficulty in driving, reading, and even recognizing faces. This necessitates the development of rapid and dependable diagnosis and treatment solutions for ocular illnesses. Previously, such visual illness diagnosis were done manually, which was time-consuming and prone to human mistake. However, as technology advances, automated, computer-based methods that decrease both time and human labor while producing trustworthy results are now accessible. In this study, we developed a CNN-LSTM-based model architecture with the goal of creating a low-cost diagnostic system that can classify normal and cataractous cases of ocular disease from fundus images. The proposed model was trained on the publicly available ODIR dataset, which included fundus images of patients' left and right eyes. The suggested architecture outperformed previous systems with a state-of-the-art 97.53% accuracy.
System Evolution Analytics on a system that evolves is a challenge because it makes a State Series SS = {S1, S2... SN} (i.e., a set of states ordered by time) with several inter-connected entities changing over time. We present stability characteristics of interesting evolution rules occurring in multiple states. We defined an evolution rule with its stability as the fraction of states in which the rule is interesting. Extensively, we defined stable rule as the evolution rule having stability that exceeds a given threshold minimum stability (minStab). We also defined persistence metric, a quantitative measure of persistent entity-connections. We explain this with an approach and algorithm for System Network Analytics (SysNet-Analytics), which uses minStab to retrieve Network Evolution Rules (NERs) and Stable NERs (SNERs). The retrieved information is used to calculate a proposed System Network Persistence (SNP) metric. This work is automated as a SysNet-Analytics Tool to demonstrate application on real world systems including: software system, natural-language system, retail market system, and IMDb system. We quantified stability and persistence of entity-connections in a system state series. This results in evolution information, which helps in system evolution analytics based on knowledge discovery and data mining.
Multi-armed bandit (MAB) problems are mainly studied under two extreme settings known as stochastic and adversarial. These two settings, however, do not capture realistic environments such as search engines and marketing and advertising, in which rewards stochastically change in time. Motivated by that, we introduce and study a dynamic MAB problem with stochastic temporal structure, where the expected reward of each arm is governed by an auto-regressive (AR) model. Due to the dynamic nature of the rewards, simple "explore and commit" policies fail, as all arms have to be explored continuously over time. We formalize this by characterizing a per-round regret lower bound, where the regret is measured against a strong (dynamic) benchmark. We then present an algorithm whose per-round regret almost matches our regret lower bound. Our algorithm relies on two mechanisms: (i) alternating between recently pulled arms and unpulled arms with potential, and (ii) restarting. These mechanisms enable the algorithm to dynamically adapt to changes and discard irrelevant past information at a suitable rate. In numerical studies, we further demonstrate the strength of our algorithm under different types of non-stationary settings.
This paper aims to develop resilient transmission mechanisms to suitably distribute traffic across multiple paths in an arbitrary millimeter-wave (mmWave) network. The main contributions include: (a) the development of proactive transmission mechanisms that build resilience against network disruptions in advance, while achieving a high end-to-end packet rate; (b) the design of a heuristic path selection algorithm that efficiently selects (in polynomial time in the network size) multiple proactively resilient paths with high packet rates; and (c) the development of a hybrid scheduling algorithm that combines the proposed path selection algorithm with a deep reinforcement learning (DRL) based online approach for decentralized adaptation to blocked links and failed paths. To achieve resilience to link failures, a state-of-the-art Soft Actor-Critic DRL algorithm, which adapts the information flow through the network, is investigated. The proposed scheduling algorithm robustly adapts to link failures over different topologies, channel and blockage realizations while offering a superior performance to alternative algorithms.
Power sector decarbonization plays a vital role in the upcoming energy transition towards a more sustainable future. Decentralized energy resources, such as Electric Vehicles (EV) and solar photovoltaic systems (PV), are continuously integrated in residential power systems, increasing the risk of bottlenecks in power distribution networks. This paper aims to address the challenge of domestic EV charging while prioritizing clean, solar energy consumption. Real Time-of-Use tariffs are treated as a price-based Demand Response (DR) mechanism that can incentivize end-users to optimally shift EV charging load in hours of high solar PV generation with the use of Deep Reinforcement Learning (DRL). Historical measurements from the Pecan Street dataset are analyzed to shape a flexibility potential reward to describe end-user charging preferences. Experimental results show that the proposed DQN EV optimal charging policy is able to reduce electricity bills by an average 11.5\% by achieving an average utilization of solar power 88.4
Neural Stochastic Differential Equations (NSDE) have been trained as both Variational Autoencoders, and as GANs. However, the resulting Stochastic Differential Equations can be hard to interpret or analyse due to the generic nature of the drift and diffusion fields. By restricting our NSDE to be of the form of Langevin dynamics, and training it as a VAE, we obtain NSDEs that lend themselves to more elaborate analysis and to a wider range of visualisation techniques than a generic NSDE. More specifically, we obtain an energy landscape, the minima of which are in one-to-one correspondence with latent states underlying the used data. This not only allows us to detect states underlying the data dynamics in an unsupervised manner, but also to infer the distribution of time spent in each state according to the learned SDE. More in general, restricting an NSDE to Langevin dynamics enables the use of a large set of tools from computational molecular dynamics for the analysis of the obtained results.