Verizon Media (VZM) native advertising is one of VZM largest and fastest growing businesses, reaching a run-rate of several hundred million USDs in the past year. Driving the VZM native models that are used to predict event probabilities, such as click and conversion probabilities, is OFFSET - a feature enhanced collaborative-filtering based event-prediction algorithm. In this work we focus on the challenge of predicting click-through rates (CTR) when we are aware that some of the clicks have short dwell-time and are defined as accidental clicks. An accidental click implies little affinity between the user and the ad, so predicting that similar users will click on the ad is inaccurate. Therefore, it may be beneficial to remove clicks with dwell-time lower than a predefined threshold from the training set. However, we cannot ignore these positive events, as filtering these will cause the model to under predict. Previous approaches have tried to apply filtering and then adding corrective biases to the CTR predictions, but did not yield revenue lifts and therefore were not adopted. In this work, we present a new approach where the positive weight of the accidental clicks is distributed among all of the negative events (skips), based on their likelihood of causing accidental clicks, as predicted by an auxiliary model. These likelihoods are taken as the correct labels of the negative events, shifting our training from using only binary labels and adopting a binary cross-entropy loss function in our training process. After showing offline performance improvements, the modified model was tested online serving VZM native users, and provided 1.18% revenue lift over the production model which is agnostic to accidental clicks.
相關內容
Interactive visual grounding in Human-Robot Interaction (HRI) is challenging yet practical due to the inevitable ambiguity in natural languages. It requires robots to disambiguate the user input by active information gathering. Previous approaches often rely on predefined templates to ask disambiguation questions, resulting in performance reduction in realistic interactive scenarios. In this paper, we propose TiO, an end-to-end system for interactive visual grounding in human-robot interaction. Benefiting from a unified formulation of visual dialogue and grounding, our method can be trained on a joint of extensive public data, and show superior generality to diversified and challenging open-world scenarios. In the experiments, we validate TiO on GuessWhat?! and InViG benchmarks, setting new state-of-the-art performance by a clear margin. Moreover, we conduct HRI experiments on the carefully selected 150 challenging scenes as well as real-robot platforms. Results show that our method demonstrates superior generality to diversified visual and language inputs with a high success rate. Codes and demos are available at //github.com/jxu124/TiO.
Adaptive Systems (ASs) are capable to monitor their behavior and make adjustments when quality goals are not achieved through the MAPE-K, a widely recognized reference model that offers abstractions for designing ASs. By making these abstractions evident in the system structure, numerous benefits emerge, particularly in terms of enhancing the architecture's maintenance and comprehensibility. However, it is observed that many existing ASs are not designed in accordance with MAPE-K, causing these abstractions to remain hidden in their architecture. To address this issue, Architectural Conformance Checking (ACC) emerges as a valuable technique for verifying whether the current architecture (CA) of a system adheres to the rules prescribed by the planned architecture (PA) or a reference model, such as MAPE-K. In this paper, we present REMEDY, a domain-specific approach that encompasses the specification of the planned adaptive architecture based on the MAPE-K reference model, the recovery of the current adaptive architecture, the conformance checking process, and architecture visualizations. Furthermore, our approach is specifically tailored for ASs, incorporating well-known rules from the MAPE-K model. The evaluation of the REMEDY DSL involves a comparison with a general-purpose DSL, and the results demonstrate improvements in productivity. REMEDY facilitates the identification and correction of architectural non-conformance issues, thereby enhancing the overall quality of adaptive systems.
Creating and maximizing influence among the customers is one of the central goals of an advertiser, and hence, remains an active area of research in recent times. In this advertisement technique, the advertisers approach an influence provider for a specific number of views of their content on a payment basis. Now, if the influence provider can provide the required number of views or more, he will receive the full, else a partial payment. In the context of an influence provider, it is a loss for him if he offers more or less views. This is formalized as 'Regret', and naturally, in the context of the influence provider, the goal will be to minimize this quantity. In this paper, we solve this problem in the context of billboard advertisement and pose it as a discrete optimization problem. We propose four efficient solution approaches for this problem and analyze them to understand their time and space complexity. We implement all the solution methodologies with real-life datasets and compare the obtained results with the existing solution approaches from the literature. We observe that the proposed solutions lead to less regret while taking less computational time.
Industrial Ethernet is a technology widely spread in factory floors and critical infrastructures where a high amount of data need to be collected and transported. Fiber optic networks at gigabit rates fit well with that type of environments where speed, system performance and reliability are critical. In this work a new encryption method for high speed optical communications suitable for such kind of networks is proposed. This new encryption method consists of a symmetric streaming encryption of the 8b/10b data flow at PCS (Physical Coding Sublayer) level. It is carried out thanks to an FPE (Format Preserving Encryption) blockcipher working in CTR (Counter) mode. The overall system has been simulated and implemented in an FPGA (Field Programmable Gate Array). Thanks to experimental results it can be concluded that it is possible to cipher traffic at this physical level in a secure way. In addition, no overhead is introduced during encryption, getting minimum latency and maximum throughput.
Organizations execute decisions within business processes on a daily basis whilst having to take into account multiple stakeholders who might require multiple point of views of the same process. Moreover, the complexity of the information systems running these business processes is generally high as they are linked to databases storing all the relevant data and aspects of the processes. Given the presence of multiple objects within an information system which support the processes in their enactment, decisions are naturally influenced by both these perspectives, logged in object-centric process logs. However, the discovery of such decisions from object-centric process logs is not straightforward as it requires to correctly link the involved objects whilst considering the sequential constraints that business processes impose as well as correctly discovering what a decision actually does. This paper proposes the first object-centric decision-mining algorithm called Integrated Object-centric Decision Discovery Algorithm (IODDA). IODDA is able to discover how a decision is structured as well as how a decision is made. Moreover, IODDA is able to discover which activities and object types are involved in the decision-making process. Next, IODDA is demonstrated with the first artificial knowledge-intensive process logs whose log generators are provided to the research community.
Crowdsourcing services, such as Waze and Google Maps, leverage a mass of mobile users to learn massive point-of-interest (PoI) information while traveling and share it as a public good. Given that crowdsourced users mind their travel costs and possess various preferences over the PoI information along different paths, we formulate the problem as a novel non-atomic multi-path routing game with positive network externalities among users in social information sharing, which distinguishes itself from the routing game literature. In the absence of any incentive design, our price of anarchy (PoA) analysis shows that users' selfish routing on the path with the lowest cost will limit information diversity and lead to an arbitrarily large efficiency loss from the social optimum. This motivates us to design effective incentive mechanisms to remedy while upholding desirable properties such as individual rationality, incentive compatibility, and budget balance for practical feasibility. Moreover, our mechanisms are designed with incomplete information, as they do not rely on individual user's path preferences, thereby ensuring user privacy. To start with, we present a non-monetary mechanism called Adaptive Information Restriction (AIR) that imposes fractions on users' access to the public good as an indirect penalty. By adapting penalty fractions to the actual user flows along different paths, our AIR achieves the first PoA of $\frac{1}{4}$ for the problem. Then, we delve into a monetary mechanism called Adaptive Side-Payment (ASP) that charges or rewards side payments over users choosing certain paths. With those side payments well-tailored, ASP significantly improves the PoA to $\frac{1}{2}$.
While Reinforcement Learning (RL) achieves tremendous success in sequential decision-making problems of many domains, it still faces key challenges of data inefficiency and the lack of interpretability. Interestingly, many researchers have leveraged insights from the causality literature recently, bringing forth flourishing works to unify the merits of causality and address well the challenges from RL. As such, it is of great necessity and significance to collate these Causal Reinforcement Learning (CRL) works, offer a review of CRL methods, and investigate the potential functionality from causality toward RL. In particular, we divide existing CRL approaches into two categories according to whether their causality-based information is given in advance or not. We further analyze each category in terms of the formalization of different models, ranging from the Markov Decision Process (MDP), Partially Observed Markov Decision Process (POMDP), Multi-Arm Bandits (MAB), and Dynamic Treatment Regime (DTR). Moreover, we summarize the evaluation matrices and open sources while we discuss emerging applications, along with promising prospects for the future development of CRL.
Vast amount of data generated from networks of sensors, wearables, and the Internet of Things (IoT) devices underscores the need for advanced modeling techniques that leverage the spatio-temporal structure of decentralized data due to the need for edge computation and licensing (data access) issues. While federated learning (FL) has emerged as a framework for model training without requiring direct data sharing and exchange, effectively modeling the complex spatio-temporal dependencies to improve forecasting capabilities still remains an open problem. On the other hand, state-of-the-art spatio-temporal forecasting models assume unfettered access to the data, neglecting constraints on data sharing. To bridge this gap, we propose a federated spatio-temporal model -- Cross-Node Federated Graph Neural Network (CNFGNN) -- which explicitly encodes the underlying graph structure using graph neural network (GNN)-based architecture under the constraint of cross-node federated learning, which requires that data in a network of nodes is generated locally on each node and remains decentralized. CNFGNN operates by disentangling the temporal dynamics modeling on devices and spatial dynamics on the server, utilizing alternating optimization to reduce the communication cost, facilitating computations on the edge devices. Experiments on the traffic flow forecasting task show that CNFGNN achieves the best forecasting performance in both transductive and inductive learning settings with no extra computation cost on edge devices, while incurring modest communication cost.
For better user experience and business effectiveness, Click-Through Rate (CTR) prediction has been one of the most important tasks in E-commerce. Although extensive CTR prediction models have been proposed, learning good representation of items from multimodal features is still less investigated, considering an item in E-commerce usually contains multiple heterogeneous modalities. Previous works either concatenate the multiple modality features, that is equivalent to giving a fixed importance weight to each modality; or learn dynamic weights of different modalities for different items through technique like attention mechanism. However, a problem is that there usually exists common redundant information across multiple modalities. The dynamic weights of different modalities computed by using the redundant information may not correctly reflect the different importance of each modality. To address this, we explore the complementarity and redundancy of modalities by considering modality-specific and modality-invariant features differently. We propose a novel Multimodal Adversarial Representation Network (MARN) for the CTR prediction task. A multimodal attention network first calculates the weights of multiple modalities for each item according to its modality-specific features. Then a multimodal adversarial network learns modality-invariant representations where a double-discriminators strategy is introduced. Finally, we achieve the multimodal item representations by combining both modality-specific and modality-invariant representations. We conduct extensive experiments on both public and industrial datasets, and the proposed method consistently achieves remarkable improvements to the state-of-the-art methods. Moreover, the approach has been deployed in an operational E-commerce system and online A/B testing further demonstrates the effectiveness.
How can we estimate the importance of nodes in a knowledge graph (KG)? A KG is a multi-relational graph that has proven valuable for many tasks including question answering and semantic search. In this paper, we present GENI, a method for tackling the problem of estimating node importance in KGs, which enables several downstream applications such as item recommendation and resource allocation. While a number of approaches have been developed to address this problem for general graphs, they do not fully utilize information available in KGs, or lack flexibility needed to model complex relationship between entities and their importance. To address these limitations, we explore supervised machine learning algorithms. In particular, building upon recent advancement of graph neural networks (GNNs), we develop GENI, a GNN-based method designed to deal with distinctive challenges involved with predicting node importance in KGs. Our method performs an aggregation of importance scores instead of aggregating node embeddings via predicate-aware attention mechanism and flexible centrality adjustment. In our evaluation of GENI and existing methods on predicting node importance in real-world KGs with different characteristics, GENI achieves 5-17% higher NDCG@100 than the state of the art.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191