Evaluating clustering quality with reliable evaluation metrics like normalized mutual information (NMI) requires labeled data that can be expensive to annotate. We focus on the underexplored problem of estimating clustering quality with limited labels. We adapt existing approaches from the few-sample model evaluation literature to actively sub-sample, with a learned surrogate model, the most informative data points for annotation to estimate the evaluation metric. However, we find that their estimation can be biased and only relies on the labeled data. To that end, we introduce CEREAL, a comprehensive framework for few-sample clustering evaluation that extends active sampling approaches in three key ways. First, we propose novel NMI-based acquisition functions that account for the distinctive properties of clustering and uncertainties from a learned surrogate model. Next, we use ideas from semi-supervised learning and train the surrogate model with both the labeled and unlabeled data. Finally, we pseudo-label the unlabeled data with the surrogate model. We run experiments to estimate NMI in an active sampling pipeline on three datasets across vision and language. Our results show that CEREAL reduces the area under the absolute error curve by up to 57% compared to the best sampling baseline. We perform an extensive ablation study to show that our framework is agnostic to the choice of clustering algorithm and evaluation metric. We also extend CEREAL from clusterwise annotations to pairwise annotations. Overall, CEREAL can efficiently evaluate clustering with limited human annotations.

Multi-source domain adaptation (MSDA) learns to predict the labels in target domain data, under the setting that data from multiple source domains are labelled and data from the target domain are unlabelled. Most methods for this task focus on learning invariant representations across domains. However, their success relies heavily on the assumption that the label distribution remains consistent across domains, which may not hold in general real-world problems. In this paper, we propose a new and more flexible assumption, termed \textit{latent covariate shift}, where a latent content variable $\mathbf{z}_c$ and a latent style variable $\mathbf{z}_s$ are introduced in the generative process, with the marginal distribution of $\mathbf{z}_c$ changing across domains and the conditional distribution of the label given $\mathbf{z}_c$ remaining invariant across domains. We show that although (completely) identifying the proposed latent causal model is challenging, the latent content variable can be identified up to scaling by using its dependence with labels from source domains, together with the identifiability conditions of nonlinear ICA. This motivates us to propose a novel method for MSDA, which learns the invariant label distribution conditional on the latent content variable, instead of learning invariant representations. Empirical evaluation on simulation and real data demonstrates the effectiveness of the proposed method.

Voice user interfaces and digital assistants are rapidly entering our lives and becoming singular touch points spanning our devices. These always-on services capture and transmit our audio data to powerful cloud services for further processing and subsequent actions. Our voices and raw audio signals collected through these devices contain a host of sensitive paralinguistic information that is transmitted to service providers regardless of deliberate or false triggers. As our emotional patterns and sensitive attributes like our identity, gender, well-being, are easily inferred using deep acoustic models, we encounter a new generation of privacy risks by using these services. One approach to mitigate the risk of paralinguistic-based privacy breaches is to exploit a combination of cloud-based processing with privacy-preserving, on-device paralinguistic information learning and filtering before transmitting voice data. In this paper we introduce EDGY, a configurable, lightweight, disentangled representation learning framework that transforms and filters high-dimensional voice data to identify and contain sensitive attributes at the edge prior to offloading to the cloud. We evaluate EDGY's on-device performance and explore optimization techniques, including model quantization and knowledge distillation, to enable private, accurate and efficient representation learning on resource-constrained devices. Our results show that EDGY runs in tens of milliseconds with 0.2% relative improvement in "zero-shot" ABX score or minimal performance penalties of approximately 5.95% word error rate (WER) in learning linguistic representations from raw voice signals, using a CPU and a single-core ARM processor without specialized hardware.

INTRODUCTION Adaptive planning is ideally suited for the deep uncertainties presented by climate change. While there is a robust scholarship on the theory and methods of adaptive planning, this has largely neglected how adaptive planning is affected by existing planning institutions and how to move forward within the constraints of traditional planning organizations. This study asks: How do existing traditional planning institutions support adaptive planning? We explore this for flood planning in the Lower Rio Grande Valley of Texas, United States. We draw on county hazard plan and regional flood plan documents as well as transcripts of regional flood planning meetings to explore the emergent topics of these institutional outputs. Using Natural Language Processing to analyze this large amount of text, we find that hazard plans and discussions developing these plans are largely lacking an adaptive approach. KEYWORDS adaptive planning; uncertainty; flood plan; Rio Grande Valley INTRODUCTION Planning for natural hazard risk reduction in the context climate change involves decision making under conditions of interacting, multiple uncertainties. Some of these are "deep uncertainties" connected to long time horizons, nonlinear changes in climates and ecosystems, and inability to reliably quantify the rate and magnitude of climate changes (Babovic & Mijic, 2018; Bosomworth & Gaillard, 2019). Other uncertainties are associated with the ambiguities and unpredictability of socioeconomic systems, including population growth, land use change, social conflict, and the whims of political will (Babovic & Mijic 2019; Buurman & Babovic, 2014). In the face of these uncertainties, a new paradigm of decision making has emerged that emphasizes the development of adaptive plans and policies (Hassnoot et al., 2013; Walker et al., 2013). Traditional planning approaches typically generate a static optimal plan to reduce vulnerability to a single'most likely' future or to respond a wide range of plausible future scenarios (Haasnoot et al., 2013; Manocha & Babovic, 2018). Because the future is largely unknowable, static optimal plans are likely to fail and adaptations are made adhoc to adjust to emerging risk conditions (Haasnoot et al., 2013).

Decision trees (DTs) epitomize the ideal of interpretability of machine learning (ML) models. The interpretability of decision trees motivates explainability approaches by so-called intrinsic interpretability, and it is at the core of recent proposals for applying interpretable ML models in high-risk applications. The belief in DT interpretability is justified by the fact that explanations for DT predictions are generally expected to be succinct. Indeed, in the case of DTs, explanations correspond to DT paths. Since decision trees are ideally shallow, and so paths contain far fewer features than the total number of features, explanations in DTs are expected to be succinct, and hence interpretable. This paper offers both theoretical and experimental arguments demonstrating that, as long as interpretability of decision trees equates with succinctness of explanations, then decision trees ought not be deemed interpretable. The paper introduces logically rigorous path explanations and path explanation redundancy, and proves that there exist functions for which decision trees must exhibit paths with arbitrarily large explanation redundancy. The paper also proves that only a very restricted class of functions can be represented with DTs that exhibit no explanation redundancy. In addition, the paper includes experimental results substantiating that path explanation redundancy is observed ubiquitously in decision trees, including those obtained using different tree learning algorithms, but also in a wide range of publicly available decision trees. The paper also proposes polynomial-time algorithms for eliminating path explanation redundancy, which in practice require negligible time to compute. Thus, these algorithms serve to indirectly attain irreducible, and so succinct, explanations for decision trees.

Online hate speech detection has become an important issue due to the growth of online content, but resources in languages other than English are extremely limited. We introduce K-MHaS, a new multi-label dataset for hate speech detection that effectively handles Korean language patterns. The dataset consists of 109k utterances from news comments and provides a multi-label classification using 1 to 4 labels, and handles subjectivity and intersectionality. We evaluate strong baseline experiments on K-MHaS using Korean-BERT-based language models with six different metrics. KR-BERT with a sub-character tokenizer outperforms others, recognizing decomposed characters in each hate speech class.

Evaluating hypothetical statements about how the world would be had a different course of action been taken is arguably one key capability expected from modern AI systems. Counterfactual reasoning underpins discussions in fairness, the determination of blame and responsibility, credit assignment, and regret. In this paper, we study the evaluation of counterfactual statements through neural models. Specifically, we tackle two causal problems required to make such evaluations, i.e., counterfactual identification and estimation from an arbitrary combination of observational and experimental data. First, we show that neural causal models (NCMs) are expressive enough and encode the structural constraints necessary for performing counterfactual reasoning. Second, we develop an algorithm for simultaneously identifying and estimating counterfactual distributions. We show that this algorithm is sound and complete for deciding counterfactual identification in general settings. Third, considering the practical implications of these results, we introduce a new strategy for modeling NCMs using generative adversarial networks. Simulations corroborate with the proposed methodology.

They Shall Not Grow Old, a 2018 documentary about the lives and aspirations of British and New Zealand soldiers living through World War I from acclaimed Lord of the Rings director Peter Jackson, had its hundred-plus-year-old silent footage modernized through both colorization and the recording of new audio for previously non-existent dialog. To get an idea of what the folks featured in the archival footage were saying, Jackson hired a team of forensic lip readers to guesstimate their recorded utterances. Reportedly, "the lip readers were so precise they were even able to determine the dialect and accent of the people speaking." "These blokes did not live in a black and white, silent world, and this film is not about the war; it's about the soldier's experience fighting the war," Jackson told the Daily Sentinel in 2018. "I wanted the audience to see, as close as possible, what the soldiers saw, and how they saw it, and heard it."

When it comes to electrical power distribution over transmission or distribution wires, a lack of vegetation management around the powerlines can lead to high maintenance costs. Vegetation management is crucial, as uncontrolled vegetation encroachments can lead to forest fires, power outages during a storm, and so on. Identifying these maintenance spots that will need trimming or vegetation management takes time. Often, you will need to conduct a manual survey, or one partially assisted by remote sensing data. Companies must spend time, money, and resources on vegetation encroachment management.

The majority of real-world processes are spatiotemporal, and the data generated by them exhibits both spatial and temporal evolution. Weather is one of the most important processes that fall under this domain, and forecasting it has become a crucial part of our daily routine. Weather data analysis is considered the most complex and challenging task. Although numerical weather prediction models are currently state-of-the-art, they are resource intensive and time-consuming. Numerous studies have proposed time-series-based models as a viable alternative to numerical forecasts. Recent research has primarily focused on forecasting weather at a specific location. Therefore, models can only capture temporal correlations. This self-contained paper explores various methods for regional data-driven weather forecasting, i.e., forecasting over multiple latitude-longitude points to capture spatiotemporal correlations. The results showed that spatiotemporal prediction models reduced computational cost while improving accuracy; in particular, the proposed tensor train dynamic mode decomposition-based forecasting model has comparable accuracy to ConvLSTM without the need for training. We use the NASA POWER meteorological dataset to evaluate the models and compare them with the current state of the art.