亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. A large number of interpreting methods focus on identifying explanatory input features, which generally fall into two main categories: attribution and selection. A popular attribution-based approach is to exploit local neighborhoods for learning instance-specific explainers in an additive manner. The process is thus inefficient and susceptible to poorly-conditioned samples. Meanwhile, many selection-based methods directly optimize local feature distributions in an instance-wise training framework, thereby being capable of leveraging global information from other inputs. However, they can only interpret single-class predictions and many suffer from inconsistency across different settings, due to a strict reliance on a pre-defined number of features selected. This work exploits the strengths of both methods and proposes a framework for learning local explanations simultaneously for multiple target classes. Our model explainer significantly outperforms additive and instance-wise counterparts on faithfulness with more compact and comprehensible explanations. We also demonstrate the capacity to select stable and important features through extensive experiments on various data sets and black-box model architectures.

Notifications are important for the user experience in mobile apps and can influence their engagement. However, too many notifications can be disruptive for users. A typical mobile app usually has several types of notification, managed by distinct teams with objectives that are possibly conflicting with each other, or even with the overall platform objective. Therefore, there is a need for careful curation of notifications sent to users of these different types. In this work, we study a novel centralized approach for notification optimization, where we view the opportunities to send user notifications as items and types of notifications as buyers in an auction market. Furthermore, the auction setup is unique, and the platform has the ability to subsidize the bids from the notification types. Using tools from fair division, we study the application of competitive equilibrium for addressing this problem. We show that an Eisenberg-Gale-style convex program allows us to find an allocation that is fair to all notification types in hindsight. Using the dual of the formulation, we present an online algorithm that allocates notifications via first-price auctions using a pacing-multiplier approach. Secondly, we introduce an approach based on second-price auctions and pacing, which has the benefit of working well with existing advertising systems built for second-price auctions. Through an A/B test in production, we show that the second price-based auction system improves over a decentralized notification optimization system, leading to its launch in production for some Instagram notifications. Further, through simulations on Instagram notification data and a subsequent production A/B test, we compare the outcomes of first-price and second-price auctions and show that the former has more stable pacing multipliers.

We present ATC, a C++ library for advanced Tucker-based lossy compression of dense multidimensional numerical data in a shared-memory parallel setting, based on the sequentially truncated higher-order singular value decomposition (ST-HOSVD) and bit plane truncation. Several techniques are proposed to improve speed, memory usage, error control and compression rate. First, a hybrid truncation scheme is described which combines Tucker rank truncation and TTHRESH quantization [Ballester-Ripoll et al., IEEE Trans. Visual. Comput. Graph., 2020]. We derive a novel expression to approximate the error of truncated Tucker decompositions in the case of core and factor perturbations. Furthermore, we parallelize the quantization and encoding scheme and adjust this phase to improve error control. Moreover, implementation aspects are described, such as an ST-HOSVD procedure using only a single transposition. We also discuss several usability features of ATC, including the presence of multiple interfaces, extensive data type support and integrated downsampling of the decompressed data. Numerical results show that ATC maintains state-of-the-art Tucker compression rates, while providing average speed-up factors of 2.2-3.5 and halving memory usage. Furthermore, our compressor provides precise error control, only deviating 1.4% from the requested error on average. Finally, ATC often achieves higher compression than non-Tucker-based compressors in the high-error domain.

Recommendation systems have become popular and effective tools to help users discover their interesting items by modeling the user preference and item property based on implicit interactions (e.g., purchasing and clicking). Humans perceive the world by processing the modality signals (e.g., audio, text and image), which inspired researchers to build a recommender system that can understand and interpret data from different modalities. Those models could capture the hidden relations between different modalities and possibly recover the complementary information which can not be captured by a uni-modal approach and implicit interactions. The goal of this survey is to provide a comprehensive review of the recent research efforts on the multimodal recommendation. Specifically, it shows a clear pipeline with commonly used techniques in each step and classifies the models by the methods used. Additionally, a code framework has been designed that helps researchers new in this area to understand the principles and techniques, and easily runs the SOTA models. Our framework is located at: //github.com/enoche/MMRec

Topos is an open interoperability protocol designed to reduce as much as possible trust assumptions by replacing them with cryptographic constructions and decentralization while exhibiting massive scalability. The protocol does not make use of a central blockchain, nor uses consensus to ensure consistent delivery of messages across a heterogeneous ecosystem of public and private blockchains, named subnets, but instead relies on a weak causal reliable broadcast implemented by a distributed network which we call $\textit{Transmission Control Engine}$ (TCE). The validity of cross-subnet messages is ensured by the $\textit{Universal Certificate Interface}$ (UCI) and stems from zkSTARK proofs asserting the validity of subnets' state transitions executed by the Topos zkVM. Such proofs of computational integrity are publicly verifiable by any other participants in and out the protocol such as other subnets or audit companies. The interface between the TCE and subnets leverages the ICE-FROST protocol, an innovative threshold signature scheme, whose static public key allows for uniquely identifying subnets after they register in the protocol. The Topos protocol is designed to provide $\textit{uniform security}$ to the ecosystem and to handle any type of subnets (e.g., permissioned, permissionless) in order to fit any business use cases and pave the way for global adoption and a new standard for the Internet base layer.

Typestates are a notion of behavioral types that describe protocols for stateful objects, specifying the available methods for each state, in terms of a state machine. Usually, objects with protocol are either forced to be used in a linear way, which restricts what a programmer can do, or deductive verification is required to verify programs where these objects may be aliased. To evaluate the strengths and limitations of static verification tools for object-oriented languages in checking the correct use of shared objects with protocol, we present a survey on four tools for Java: VeriFast, VerCors, Plural, and KeY. We describe the implementation of a file reader and of a linked-list, check for each tool its ability to statically guarantee protocol compliance as well as protocol completion, even when objects are shared in collections, and evaluate the programmer's effort in making the code acceptable to these tools.

Based on a case study on 3D printing, we have been experimenting on the sonification of multidimensional data for peripheral process monitoring. In a previous paper, we tested the effectiveness of a soundscape which combined intentionally incongruous natural and musical sounds. This was based on the hypothesis that auditory stimuli could better stand out from one another if they were less ecologically coherent, thus allowing for better reaction rates to various notifications. In this paper, we follow up on that hypothesis by testing two new acoustic ecologies, each exclusively consisting of either musical or natural sounds. We then run those ecologies through the same dual-task evaluation process as the previous one in order to compare them. The results seem to favor our hypothesis, as the new ecologies were not detected as accurately as the original. Though, the set of natural sounds seemed to be considered less intrusive by testers, and to allow for a better performance at an external primary task. We hope to see this work become part of a much larger corpus of studies, which may eventually provide a more definite answer on the effect of ecological coherence in peripheral soundscape design.

Federated learning (FL) is an emerging, privacy-preserving machine learning paradigm, drawing tremendous attention in both academia and industry. A unique characteristic of FL is heterogeneity, which resides in the various hardware specifications and dynamic states across the participating devices. Theoretically, heterogeneity can exert a huge influence on the FL training process, e.g., causing a device unavailable for training or unable to upload its model updates. Unfortunately, these impacts have never been systematically studied and quantified in existing FL literature. In this paper, we carry out the first empirical study to characterize the impacts of heterogeneity in FL. We collect large-scale data from 136k smartphones that can faithfully reflect heterogeneity in real-world settings. We also build a heterogeneity-aware FL platform that complies with the standard FL protocol but with heterogeneity in consideration. Based on the data and the platform, we conduct extensive experiments to compare the performance of state-of-the-art FL algorithms under heterogeneity-aware and heterogeneity-unaware settings. Results show that heterogeneity causes non-trivial performance degradation in FL, including up to 9.2% accuracy drop, 2.32x lengthened training time, and undermined fairness. Furthermore, we analyze potential impact factors and find that device failure and participant bias are two potential factors for performance degradation. Our study provides insightful implications for FL practitioners. On the one hand, our findings suggest that FL algorithm designers consider necessary heterogeneity during the evaluation. On the other hand, our findings urge system providers to design specific mechanisms to mitigate the impacts of heterogeneity.

The difficulty of deploying various deep learning (DL) models on diverse DL hardwares has boosted the research and development of DL compilers in the community. Several DL compilers have been proposed from both industry and academia such as Tensorflow XLA and TVM. Similarly, the DL compilers take the DL models described in different DL frameworks as input, and then generate optimized codes for diverse DL hardwares as output. However, none of the existing survey has analyzed the unique design of the DL compilers comprehensively. In this paper, we perform a comprehensive survey of existing DL compilers by dissecting the commonly adopted design in details, with emphasis on the DL oriented multi-level IRs, and frontend/backend optimizations. Specifically, we provide a comprehensive comparison among existing DL compilers from various aspects. In addition, we present detailed analysis of the multi-level IR design and compiler optimization techniques. Finally, several insights are highlighted as the potential research directions of DL compiler. This is the first survey paper focusing on the unique design of DL compiler, which we hope can pave the road for future research towards the DL compiler.

Meta-learning extracts the common knowledge acquired from learning different tasks and uses it for unseen tasks. It demonstrates a clear advantage on tasks that have insufficient training data, e.g., few-shot learning. In most meta-learning methods, tasks are implicitly related via the shared model or optimizer. In this paper, we show that a meta-learner that explicitly relates tasks on a graph describing the relations of their output dimensions (e.g., classes) can significantly improve the performance of few-shot learning. This type of graph is usually free or cheap to obtain but has rarely been explored in previous works. We study the prototype based few-shot classification, in which a prototype is generated for each class, such that the nearest neighbor search between the prototypes produces an accurate classification. We introduce "Gated Propagation Network (GPN)", which learns to propagate messages between prototypes of different classes on the graph, so that learning the prototype of each class benefits from the data of other related classes. In GPN, an attention mechanism is used for the aggregation of messages from neighboring classes, and a gate is deployed to choose between the aggregated messages and the message from the class itself. GPN is trained on a sequence of tasks from many-shot to few-shot generated by subgraph sampling. During training, it is able to reuse and update previously achieved prototypes from the memory in a life-long learning cycle. In experiments, we change the training-test discrepancy and test task generation settings for thorough evaluations. GPN outperforms recent meta-learning methods on two benchmark datasets in all studied cases.