Multiple lines of evidence suggest that predictive models may benefit from algorithmic triage. Under algorithmic triage, a predictive model does not predict all instances but instead defers some of them to human experts. However, the interplay between the prediction accuracy of the model and the human experts under algorithmic triage is not well understood. In this work, we start by formally characterizing under which circumstances a predictive model may benefit from algorithmic triage. In doing so, we also demonstrate that models trained for full automation may be suboptimal under triage. Then, given any model and desired level of triage, we show that the optimal triage policy is a deterministic threshold rule in which triage decisions are derived deterministically by thresholding the difference between the model and human errors on a per-instance level. Building upon these results, we introduce a practical gradient-based algorithm that is guaranteed to find a sequence of triage policies and predictive models of increasing performance. Experiments on a wide variety of supervised learning tasks using synthetic and real data from two important applications -- content moderation and scientific discovery -- illustrate our theoretical results and show that the models and triage policies provided by our gradient-based algorithm outperform those provided by several competitive baselines.

Given an optimization problem, the Hessian matrix and its eigenspectrum can be used in many ways, ranging from designing more efficient second-order algorithms to performing model analysis and regression diagnostics. When nonlinear models and non-convex problems are considered, strong simplifying assumptions are often made to make Hessian spectral analysis more tractable. This leads to the question of how relevant the conclusions of such analyses are for more realistic nonlinear models. In this paper, we exploit deterministic equivalent techniques from random matrix theory to make a \emph{precise} characterization of the Hessian eigenspectra for a broad family of nonlinear models, including models that generalize the classical generalized linear models, without relying on strong simplifying assumptions used previously. We show that, depending on the data properties, the nonlinear response model, and the loss function, the Hessian can have \emph{qualitatively} different spectral behaviors: of bounded or unbounded support, with single- or multi-bulk, and with isolated eigenvalues on the left- or right-hand side of the bulk. By focusing on such a simple but nontrivial nonlinear model, our analysis takes a step forward to unveil the theoretical origin of many visually striking features observed in more complex machine learning models.

Outlier ensemble methods have shown outstanding performance on the discovery of instances that are significantly different from the majority of the data. However, without the awareness of fairness, their applicability in the ethical scenarios, such as fraud detection and judiciary judgement system, could be degraded. In this paper, we propose to reduce the bias of the outlier ensemble results through a fairness-aware ensemble framework. Due to the lack of ground truth in the outlier detection task, the key challenge is how to mitigate the degradation in the detection performance with the improvement of fairness. To address this challenge, we define a distance measure based on the output of conventional outlier ensemble techniques to estimate the possible cost associated with detection performance degradation. Meanwhile, we propose a post-processing framework to tune the original ensemble results through a stacking process so that we can achieve a trade off between fairness and detection performance. Detection performance is measured by the area under ROC curve (AUC) while fairness is measured at both group and individual level. Experiments on eight public datasets are conducted. Results demonstrate the effectiveness of the proposed framework in improving fairness of outlier ensemble results. We also analyze the trade-off between AUC and fairness.

This paper presents SPICE, a Semantic Pseudo-labeling framework for Image ClustEring. Instead of using indirect loss functions required by the recently proposed methods, SPICE generates pseudo-labels via self-learning and directly uses the pseudo-label-based classification loss to train a deep clustering network. The basic idea of SPICE is to synergize the discrepancy among semantic clusters, the similarity among instance samples, and the semantic consistency of local samples in an embedding space to optimize the clustering network in a semantically-driven paradigm. Specifically, a semantic-similarity-based pseudo-labeling algorithm is first proposed to train a clustering network through unsupervised representation learning. Given the initial clustering results, a local semantic consistency principle is used to select a set of reliably labeled samples, and a semi-pseudo-labeling algorithm is adapted for performance boosting. Extensive experiments demonstrate that SPICE clearly outperforms the state-of-the-art methods on six common benchmark datasets including STL10, Cifar10, Cifar100-20, ImageNet-10, ImageNet-Dog, and Tiny-ImageNet. On average, our SPICE method improves the current best results by about 10% in terms of adjusted rand index, normalized mutual information, and clustering accuracy.

This paper presents a new dataset of Peter the Great's manuscripts and describes a segmentation procedure that converts initial images of documents into the lines. The new dataset may be useful for researchers to train handwriting text recognition models as a benchmark for comparing different models. It consists of 9 694 images and text files corresponding to lines in historical documents. The open machine learning competition Digital Peter was held based on the considered dataset. The baseline solution for this competition as well as more advanced methods on handwritten text recognition are described in the article. Full dataset and all code are publicly available.

There are demographic biases in the SOTA CNN used for FR. Our BFW dataset serves as a proxy to measure bias across ethnicity and gender subgroups, allowing us to characterize FR performances per subgroup. We show performances are non-optimal when a single score threshold is used to determine whether sample pairs are genuine or imposter. Furthermore, actual performance ratings vary greatly from the reported across subgroups. Thus, claims of specific error rates only hold true for populations matching that of the validation data. We mitigate the imbalanced performances using a novel domain adaptation learning scheme on the facial encodings extracted using SOTA deep nets. Not only does this technique balance performance, but it also boosts the overall performance. A benefit of the proposed is to preserve identity information in facial features while removing demographic knowledge in the lower dimensional features. The removal of demographic knowledge prevents future potential biases from being injected into decision-making. Additionally, privacy concerns are satisfied by this removal. We explore why this works qualitatively with hard samples. We also show quantitatively that subgroup classifiers can no longer learn from the encodings mapped by the proposed.

Automatically and accurately identifying user intents and filling the associated slots from their spoken language are critical to the success of dialogue systems. Traditional methods require manually defining the DOMAIN-INTENT-SLOT schema and asking many domain experts to annotate the corresponding utterances, upon which neural models are trained. This procedure brings the challenges of information sharing hindering, out-of-schema, or data sparsity in open-domain dialogue systems. To tackle these challenges, we explore a new task of {\em automatic intent-slot induction} and propose a novel domain-independent tool. That is, we design a coarse-to-fine three-step procedure including Role-labeling, Concept-mining, And Pattern-mining (RCAP): (1) role-labeling: extracting keyphrases from users' utterances and classifying them into a quadruple of coarsely-defined intent-roles via sequence labeling; (2) concept-mining: clustering the extracted intent-role mentions and naming them into abstract fine-grained concepts; (3) pattern-mining: applying the Apriori algorithm to mine intent-role patterns and automatically inferring the intent-slot using these coarse-grained intent-role labels and fine-grained concepts. Empirical evaluations on both real-world in-domain and out-of-domain datasets show that: (1) our RCAP can generate satisfactory SLU schema and outperforms the state-of-the-art supervised learning method; (2) our RCAP can be directly applied to out-of-domain datasets and gain at least 76\% improvement of F1-score on intent detection and 41\% improvement of F1-score on slot filling; (3) our RCAP exhibits its power in generic intent-slot extractions with less manual effort, which opens pathways for schema induction on new domains and unseen intent-slot discovery for generalizable dialogue systems.

Quality-of-Service prediction of web service is an integral part of services computing due to its diverse applications in the various facets of a service life cycle, such as service composition, service selection, service recommendation. One of the primary objectives of designing a QoS prediction algorithm is to achieve satisfactory prediction accuracy. However, accuracy is not the only criteria to meet while developing a QoS prediction algorithm. The algorithm has to be faster in terms of prediction time so that it can be integrated into a real-time recommendation or composition system. The other important factor to consider while designing the prediction algorithm is scalability to ensure that the prediction algorithm can tackle large-scale datasets. The existing algorithms on QoS prediction often compromise on one goal while ensuring the others. In this paper, we propose a semi-offline QoS prediction model to achieve three important goals simultaneously: higher accuracy, faster prediction time, scalability. Here, we aim to predict the QoS value of service that varies across users. Our framework consists of multi-phase prediction algorithms: preprocessing-phase prediction, online prediction, and prediction using the pre-trained model. In the preprocessing phase, we first apply multi-level clustering on the dataset to obtain correlated users and services. We then preprocess the clusters using collaborative filtering to remove the sparsity of the given QoS invocation log matrix. Finally, we create a two-staged, semi-offline regression model using neural networks to predict the QoS value of service to be invoked by a user in real-time. Our experimental results on four publicly available WS-DREAM datasets show the efficiency in terms of accuracy, scalability, fast responsiveness of our framework as compared to the state-of-the-art methods.

Episodic and semantic memory are critical components of the human memory model. The theory of complementary learning systems (McClelland et al., 1995) suggests that the compressed representation produced by a serial event (episodic memory) is later restructured to build a more generalized form of reusable knowledge (semantic memory). In this work we develop a new principled Bayesian memory allocation scheme that bridges the gap between episodic and semantic memory via a hierarchical latent variable model. We take inspiration from traditional heap allocation and extend the idea of locally contiguous memory to the Kanerva Machine, enabling a novel differentiable block allocated latent memory. In contrast to the Kanerva Machine, we simplify the process of memory writing by treating it as a fully feed forward deterministic process, relying on the stochasticity of the read key distribution to disperse information within the memory. We demonstrate that this allocation scheme improves performance in memory conditional image generation, resulting in new state-of-the-art conditional likelihood values on binarized MNIST ( 41.58 nats/image), binarized Omniglot ( 66.24 nats/image), as well as presenting competitive performance on CIFAR10, DMLab Mazes, Celeb-A and ImageNet32 32. Memory is a central tenet in the model of human intelligence and is crucial to long-term reasoning and planning.

Session 1.3: K means Clustering in OpenCV Session 1.4: Reverse a Video Session 3.2: Create negative images Session 3.3: Create positive images