With the growing adoption of AI, trust and explainability have become critical which has attracted a lot of research attention over the past decade and has led to the development of many popular AI explainability libraries such as AIX360, Alibi, OmniXAI, etc. Despite that, applying explainability techniques in practice often poses challenges such as lack of consistency between explainers, semantically incorrect explanations, or scalability. Furthermore, one of the key modalities that has been less explored, both from the algorithmic and practice point of view, is time-series. Several application domains involve time-series including Industry 4.0, asset monitoring, supply chain or finance to name a few.

Locally interpretable model agnostic explanations (LIME) method is one of the most popular methods used to explain black-box models at a per example level. Although many variants have been proposed, few provide a simple way to produce high fidelity explanations that are also stable and intuitive. In this work, we provide a novel perspective by proposing a model agnostic local explanation method inspired by the invariant risk minimization (IRM) principle -- originally proposed for (global) out-of-distribution generalization -- to provide such high fidelity explanations that are also stable and unidirectional across nearby examples. Our method is based on a game theoretic formulation where we theoretically show that our approach has a strong tendency to eliminate features where the gradient of the black-box function abruptly changes sign in the locality of the example we want to explain, while in other cases it is more careful and will choose a more conservative (feature) attribution, a behavior which can be highly desirable for recourse. Empirically, we show on tabular, image and text data that the quality of our explanations with neighborhoods formed using random perturbations are much better than LIME and in some cases even comparable to other methods that use realistic neighbors sampled from the data manifold. This is desirable given that learning a manifold to either create realistic neighbors or to project explanations is typically expensive or may even be impossible. Moreover, our algorithm is simple and efficient to train, and can ascertain stable input features for local decisions of a black-box without access to side information such as a (partial) causal graph as has been seen in some recent works.

As artificial intelligence and machine learning algorithms become increasingly prevalent in society, multiple stakeholders are calling for these algorithms to provide explanations. At the same time, these stakeholders, whether they be affected citizens, government regulators, domain experts, or system developers, have different explanation needs. To address these needs, in 2019, we created AI Explainability 360, an open source software toolkit featuring ten diverse and state-of-the-art explainability methods and two evaluation metrics. This paper examines the impact of the toolkit with several case studies, statistics, and community feedback. The different ways in which users have experienced AI Explainability 360 have resulted in multiple types of impact and improvements in multiple metrics, highlighted by the adoption of the toolkit by the independent LF AI & Data Foundation. The paper also describes the flexible design of the toolkit, examples of its use, and the significant educational material and documentation available to its users.

The loosely-coupled microservices architecture has become increasingly popular due to the advantage of its modularity and elasticity in cloud applications. However, it also seriously complicates cloud management and degrades the performance of IT operations. Today, AI has been the locus of commerce and transactions, and transforming traditional IT operations for speed and growth. Inferring the dependencies among an application's microservices can greatly help SREs diagnose possible root causes of performance issues, which is a hard task due to the complex topology of microservices is often unknown in practice. Prior literature on detecting causal structure for cloud services requires significant application instrumentation, which rarely holds in reality. In this work, we leverage Granger causality models on just monitored log data of a microservice-based application to infer the impact of dependencies between microservices. We first describe the approach of modeling discrete log data as time series, and then formally define the Granger causality problem using both linear and nonlinear autoregressive models. Finally, we conduct an extensive comparative study to show the performance of the state-of-the-art linear and nonlinear (i.e., neural) Granger causality methods on both synthetic data and real-world log data from a publicly available benchmark microservice system. Our preliminary results indicate that neural Granger causality models outperform traditional Granger causality methods on both linear and nonlinear time series data, while for large linear time series, linear Granger causal models are more efficient with high accuracy. Using the real-world log data, we also demonstrate our interesting findings on inferred dependency graph of microservices by linear and neural Granger causality models.

As artificial intelligence algorithms make further inroads in high-stakes societal applications, there are increasing calls from multiple stakeholders for these algorithms to explain their outputs. To make matters more challenging, different personas of consumers of explanations have different requirements for explanations. Toward addressing these needs, we introduce AI Explainability 360, an open-source Python toolkit featuring ten diverse and state-of-the-art explainability methods and two evaluation metrics. Equally important, we provide a taxonomy to help entities requiring explanations to navigate the space of interpretation and explanation methods, not only those in the toolkit but also in the broader literature on explainability. For data scientists and other users of the toolkit, we have implemented an extensible software architecture that organizes methods according to their place in the AI modeling pipeline. The toolkit is not only the software, but also guidance material, tutorials, and an interactive web demo to introduce AI explainability to different audiences. Together, our toolkit and taxonomy can help identify gaps where more explainability methods are needed and provide a platform to incorporate them as they are developed.

Machine learning models deployed on the cloud are susceptible to several security threats including extraction attacks. Adversaries may abuse a model's prediction API to steal the model thus compromising model confidentiality, privacy of training data, and revenue from future query payments. This work introduces a model extraction monitor that quantifies the extraction status of models by continually observing the API query and response streams of users. We present two novel strategies that measure either the information gain or the coverage of the feature space spanned by user queries to estimate the learning rate of individual and colluding adversaries. Both approaches have low computational overhead and can easily be offered as services to model owners to warn them against state of the art extraction attacks. We demonstrate empirical performance results of these approaches for decision tree and neural network models using open source datasets and BigML MLaaS platform.

One of the major challenges confronting the widespread adoption of solar energy is the uncertainty of production. The energy generated by photo-voltaic systems is a function of the received solar irradiance which varies due to atmospheric and weather conditions. A key component required for forecasting irradiance accurately is the clear sky model which estimates the average irradiance at a location at a given time in the absence of clouds. Current methods for modelling clear sky irradiance are either inaccurate or require extensive atmospheric data, which tends to vary with location and is often unavailable. In this paper, we present a data-driven methodology, Blue Skies, for modelling clear sky irradiance solely based on historical irradiance measurements. Using machine learning techniques, Blue Skies is able to generate clear sky models that are more accurate spatio-temporally compared to the state of the art, reducing errors by almost 50%.

In electricity markets, the choice of the right pricing regime is crucial for the utilities because the price they charge to their consumers, in anticipation of their demand in real-time, is a key determinant of their profits and ultimately their survival in competitive energy markets. Among the existing pricing regimes, in this paper, we consider ex-ante dynamic pricing schemes as (i) they help to address the peak demand problem (a crucial problem in smart grids), and (ii) they are transparent and fair to consumers as the cost of electricity can be calculated before the actual consumption. In particular, we propose an axiomatic framework that establishes the conceptual underpinnings of the class of ex-ante dynamic pricing schemes. We first propose five key axioms that reflect the criteria that are vital for energy utilities and their relationship with consumers. We then prove an impossibility theorem to show that there is no pricing regime that satisfies all the five axioms simultaneously. We also study multiple cost functions arising from various pricing regimes to examine the subset of axioms that they satisfy. We believe that our proposed framework in this paper is first of its kind to evaluate the class of ex-ante dynamic pricing schemes in a manner that can be operationalised by energy utilities.

The connectivity model of a power distribution network can easily become outdated due to system changes occurring in the field. Maintaining and sustaining an accurate connectivity model is a key challenge for distribution utilities worldwide. This work shows that voltage time series measurements collected from customer smart meters exhibit correlations that are consistent with the hierarchical structure of the distribution network. These correlations may be leveraged to cluster customers based on common ancestry and help verify and correct an existing connectivity model. Additionally, customers may be clustered in combination with voltage data from circuit metering points, spatial data from the geographical information system, and any existing but partially accurate connectivity model to infer customer to transformer and phase connectivity relationships with high accuracy.

Managing the Quality-of-Experience (QoE) of video streaming for wireless clients is becoming increasingly important due to the rapid growth of video traffic on wireless networks. The inherent variability of the wireless channel as well as the Variable Bit Rate (VBR) of the compressed video streams make QoE management a challenging problem. In this paper, we investigate scheduling algorithms to transmit multiple video streams from a base station to mobile clients. We present an epoch-by-epoch framework to fairly allocate wireless transmission slots to streaming videos. In each epoch, our scheme reduces the vulnerability to stalling by allocating slots to videos in a way that maximizes the minimum “playout lead” across all videos. We show that the problem of allocating slots fairly is NP-complete even for a constant number of videos. We then present a fast lead-aware greedy scheduling algorithm. Our greedy algorithm is optimal when the channel quality of a user remains unchanged within an epoch. Our experimental results, based on public MPEG-4 video traces and wireless channel traces that we collected from a WiMAX test-bed, show that the lead-aware greedy approach results in a fair distribution of stalls across the clients when compared to other algorithms, while still maintaining similar or fewer average number of stalls per client.

A significant amount of energy is wasted by electrical appliances when they operate inefficiently either due to anomalies and/or incorrect usage. To address this problem, we present SocketWatch - an autonomous appliance monitoring system. SocketWatch is positioned between a wall socket and an appliance. SocketWatch learns the behavioral model of the appliance by analyzing its active and reactive power consumption patterns. It detects appliance malfunctions by observing any marked deviations from these patterns. SocketWatch is inexpensive and is easy to use: it neither requires any enhancement to the appliances nor to the power sockets nor any communication infrastructure. Moreover, the decentralized approach avoids communication latency and costs, and preserves data privacy. Real world experiments with multiple appliances indicate that SocketWatch can be an effective and inexpensive solution for reducing electricity wastage.

The Indian electricity sector, despite having the world's fifth largest installed capacity, suffers from a 12.9% peaking shortage. This shortage could be alleviated, if a large number of deferrable loads, particularly the high powered ones, could be moved from on-peak to off-peak times. However, conventional Demand Side Management (DSM) strategies may not be suitable for India as the local conditions usually favor inexpensive solutions with minimal dependence on the pre-existing infrastructure. In this work, we present a completely autonomous DSM controller called the nPlug. nPlug is positioned between the wall socket and deferrable load(s) such as water heaters, washing machines, and electric vehicles. nPlugs combine local sensing and analytics to infer peak periods as well as supply-demand imbalance conditions. They schedule attached appliances in a decentralized manner to alleviate peaks whenever possible without violating the requirements of consumers. nPlugs do not require any manual intervention by the end consumer nor any communication infrastructure nor any enhancements to the appliances or the power grids. Some of nPlug's capabilities are demonstrated using experiments on a combination of synthetic and real data collected from plug-level energy monitors. Our results indicate that nPlug can be an effective and inexpensive technology to address the peaking shortage. This technology could potentially be integrated into millions of future deferrable loads: appliances, electric vehicle (EV) chargers, heat pumps, water heaters, etc.

Managing the Quality-of-Experience (QoE) of video streaming for wireless clients is becoming increasingly important due to the rapid growth of video traffic on wireless networks. The inherent variability of the wireless channel as well as the Variable Bit Rate (VBR) of the compressed video streams make QoE management a challenging problem. Prior work has studied this problem in the context of transmitting a single video stream. In this paper, we investigate multiplexing schemes to transmit multiple video streams from a base station to mobile clients that use number of playout stalls as a performance metric. In this context, we present an epoch-by-epoch framework to fairly allocate wireless transmission slots to streaming videos. In each epoch our scheme essentially reduces the vulnerability to stalling by allocating slots to videos in a way that maximizes the minimum `playout lead' across all videos. Next, we show that the problem of allocating slots fairly is NP-complete even for a constant number of videos. We then present a fast lead-aware greedy algorithm for the problem. Our choice of greedy algorithm is motivated by the fact that this algorithm is optimal when the channel quality of a user remains unchanged within an epoch (but different users may experience different channel quality). Moreover, our experimental results based on public MPEG-4 video traces and wireless channel traces that we collected from a WiMAX test-bed show that the lead-aware greedy approach performs a fair distribution of stalls across the clients when compared to other algorithms, while still maintaining similar or lower average number of stalls per client.

Multicast-based network tomography enables inference of average loss rates and delay distributions of internal network links from end-to-end measurements of multicast probes. Recent work showed that this method, based on correlating observations of multicast receivers, also supports the inference of temporal loss characteristics of network links. In this paper, we show that temporal characteristics can, in fact, be estimated even for link delay processes. Knowledge of temporal delay characteristics has applications for delay sensitive services such as VoIP as well as for characterizing the queueing behavior of bottleneck links. By assuming mutually independent, but arbitrary link delay processes, we develop estimators which can infer, in addition to delay distributions, the probabilities of arbitrary patterns of delay, means and full distributions of delay-run periods at chosen delay levels, for each link in the multicast tree. By applying the recently proposed principle of subtree-partitioning, the estimator is made scalable to multicast trees of large degree. Estimation error and convergence rates are evaluated using simulations.

We analyze local search heuristics for the metric k-median and facility location problems. We define the locality gap of a local search procedure for a minimization problem as the maximum ratio of a locally optimum solution (obtained using this procedure) to the global optimum. For k-median, we show that local search with swaps has a locality gap of 5. Furthermore, if we permit up to p facilities to be swapped simultaneously, then the locality gap is 3+2/p. This is the first analysis of a local search for k-median that provides a bounded performance guarantee with only k medians. This also improves the previous known 4 approximation for this problem. For uncapacitated facility location, we show that local search, which permits adding, dropping, and swapping a facility, has a locality gap of 3. This improves the bound of 5 given by M. Korupolu, C. Plaxton, and R. Rajaraman [Analysis of a Local Search Heuristic for Facility Location Problems, Technical Report 98-30, DIMACS, 1998]. We also consider a capacitated facility location problem where each facility has a capacity and we are allowed to open multiple copies of a facility. For this problem we introduce a new local search operation which opens one or more copies of a facility and drops zero or more facilities. We prove that this local search has a locality gap between 3 and 4.

In this paper, we analyze local search heuristics for the k-median and facility location problems. We define the {\em locality gap\/} of a local search procedure as the maximum ratio of a locally optimum solution (obtained using this procedure) to the global optimum. For k-median, we show that local search with swaps has a locality gap of exactly 5. When we permit p facilities to be swapped simultaneously then the locality gap of the local search procedure is exactly 3+2/p. This is the first analysis of local search for k-median that provides a bounded performance guarantee with only k medians. This also improves the previous known 4 approximation for this problem. For Uncapacitated facility location, we show that local search, which permits adding, dropping and swapping a facility, has a locality gap of exactly 3. This improves the 5 bound of Korupolu et al. We also consider a capacitated facility location problem where each facilitym has a capacity and we are allowed to open multiple copies of a facility. For this problem we introduce a new operation which opens one or more copies of a facility and drops zero or more facilities. We prove that local search which permits this new operation has a locality gap between 3 and 4.