Auction-based recommender systems are prevalent in online advertising platforms, but they are typically optimized to allocate recommendation slots based on immediate expected return metrics, neglecting the downstream effects of recommendations on user behavior. In this study, we employ reinforcement learning to optimize for long-term return metrics in an auction-based recommender system. Utilizing temporal difference learning, a fundamental reinforcement learning algorithm, we implement an one-step policy improvement approach that biases the system towards recommendations with higher long-term user engagement metrics. This optimizes value over long horizons while maintaining compatibility with the auction framework. Our approach is grounded in dynamic programming ideas which show that our method provably improves upon the existing auction-based base policy. Through an online A/B test conducted on an auction-based recommender system which handles billions of impressions and users daily, we empirically establish that our proposed method outperforms the current production system in terms of long-term user engagement metrics.
相關內容
Mobile manipulators have been employed in many applications which are usually performed by multiple fixed-base robots or a large-size system, thanks to the mobility of the mobile base. However, the mobile base also brings redundancies to the system, which makes trajectory planning more challenging. One class of problems recently arising from mobile 3D printing is the trajectory-continuous tasks, in which the end-effector is required to follow a designed continuous trajectory (time-parametrized path) in task space. This paper formulates and solves the optimal trajectory planning problem for mobile manipulators under end-effector trajectory continuity constraint, which allows considerations of other constraints and trajectory optimization. To demonstrate our method, a discrete optimal trajectory planning algorithm is proposed to solve mobile 3D printing tasks in multiple experiments.
The AI community has made significant strides in developing powerful foundation models, driven by large-scale multimodal datasets. However, in the audio representation learning community, the present audio-language datasets suffer from limitations such as insufficient volume, simplistic content, and arduous collection procedures. To tackle these challenges, we present an innovative and automatic audio caption generation pipeline based on a series of public tools or APIs, and construct a large-scale, high-quality, audio-language dataset, named as Auto-ACD, comprising over 1.9M audio-text pairs. To demonstrate the effectiveness of the proposed dataset, we train popular models on our dataset and show performance improvement on various downstream tasks, namely, audio-language retrieval, audio captioning, environment classification. In addition, we establish a novel test set and provide a benchmark for audio-text tasks. The proposed dataset will be released at //auto-acd.github.io/.
Blockwise self-attentional encoder models have recently emerged as one promising end-to-end approach to simultaneous speech translation. These models employ a blockwise beam search with hypothesis reliability scoring to determine when to wait for more input speech before translating further. However, this method maintains multiple hypotheses until the entire speech input is consumed -- this scheme cannot directly show a single \textit{incremental} translation to users. Further, this method lacks mechanisms for \textit{controlling} the quality vs. latency tradeoff. We propose a modified incremental blockwise beam search incorporating local agreement or hold-$n$ policies for quality-latency control. We apply our framework to models trained for online or offline translation and demonstrate that both types can be effectively used in online mode. Experimental results on MuST-C show 0.6-3.6 BLEU improvement without changing latency or 0.8-1.4 s latency improvement without changing quality.
Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering
Despite their competitive performance on knowledge-intensive tasks, large language models (LLMs) still have limitations in memorizing all world knowledge especially long tail knowledge. In this paper, we study the KG-augmented language model approach for solving the knowledge graph question answering (KGQA) task that requires rich world knowledge. Existing work has shown that retrieving KG knowledge to enhance LLMs prompting can significantly improve LLMs performance in KGQA. However, their approaches lack a well-formed verbalization of KG knowledge, i.e., they ignore the gap between KG representations and textual representations. To this end, we propose an answer-sensitive KG-to-Text approach that can transform KG knowledge into well-textualized statements most informative for KGQA. Based on this approach, we propose a KG-to-Text enhanced LLMs framework for solving the KGQA task. Experiments on several KGQA benchmarks show that the proposed KG-to-Text augmented LLMs approach outperforms previous KG-augmented LLMs approaches regarding answer accuracy and usefulness of knowledge statements.
Mobile manipulators have been used for inspection, maintenance and repair tasks over the years, but there are some key limitations. Stability concerns typically require mobile platforms to be large in order to handle far-reaching manipulators, or for the manipulators to have drastically reduced workspaces to fit onto smaller mobile platforms. Therefore we propose a combination of two widely-used robots, the Clearpath Jackal unmanned ground vehicle and the Kinova Gen3 six degree-of-freedom manipulator. The Jackal has a small footprint and works well in low-clearance indoor environments. Extensive testing of localization, navigation and mapping using LiDAR sensors makes the Jackal a well developed mobile platform suitable for mobile manipulation. The Gen3 has a long reach with reasonable power consumption for manipulation tasks. A wrist camera for RGB-D sensing and a customizable end effector interface makes the Gen3 suitable for a myriad of manipulation tasks. Typically these features would result in an unstable platform, however with a few minor hardware and software modifications, we have produced a stable, high-performance mobile manipulation platform with significant mobility, reach, sensing, and maneuverability for indoor inspection tasks, without degradation of the component robots' individual capabilities. These assertions were investigated with hardware via semi-autonomous navigation to waypoints in a busy indoor environment, and high-precision self-alignment alongside planar structures for intervention tasks.
Analog computing has reemerged as a promising avenue for accelerating deep neural networks (DNNs) due to its potential to overcome the energy efficiency and scalability challenges posed by traditional digital architectures. However, achieving high precision and DNN accuracy using such technologies is challenging, as high-precision data converters are costly and impractical. In this paper, we address this challenge by using the residue number system (RNS). RNS allows composing high-precision operations from multiple low-precision operations, thereby eliminating the information loss caused by the limited precision of the data converters. Our study demonstrates that analog accelerators utilizing the RNS-based approach can achieve ${\geq}99\%$ of FP32 accuracy for state-of-the-art DNN inference using data converters with only $6$-bit precision whereas a conventional analog core requires more than $8$-bit precision to achieve the same accuracy in the same DNNs. The reduced precision requirements imply that using RNS can reduce the energy consumption of analog accelerators by several orders of magnitude while maintaining the same throughput and precision. Our study extends this approach to DNN training, where we can efficiently train DNNs using $7$-bit integer arithmetic while achieving accuracy comparable to FP32 precision. Lastly, we present a fault-tolerant dataflow using redundant RNS error-correcting codes to protect the computation against noise and errors inherent within an analog accelerator.
Deep reinforcement learning algorithms can perform poorly in real-world tasks due to the discrepancy between source and target environments. This discrepancy is commonly viewed as the disturbance in transition dynamics. Many existing algorithms learn robust policies by modeling the disturbance and applying it to source environments during training, which usually requires prior knowledge about the disturbance and control of simulators. However, these algorithms can fail in scenarios where the disturbance from target environments is unknown or is intractable to model in simulators. To tackle this problem, we propose a novel model-free actor-critic algorithm -- namely, state-conservative policy optimization (SCPO) -- to learn robust policies without modeling the disturbance in advance. Specifically, SCPO reduces the disturbance in transition dynamics to that in state space and then approximates it by a simple gradient-based regularizer. The appealing features of SCPO include that it is simple to implement and does not require additional knowledge about the disturbance or specially designed simulators. Experiments in several robot control tasks demonstrate that SCPO learns robust policies against the disturbance in transition dynamics.
Spatio-temporal forecasting is challenging attributing to the high nonlinearity in temporal dynamics as well as complex location-characterized patterns in spatial domains, especially in fields like weather forecasting. Graph convolutions are usually used for modeling the spatial dependency in meteorology to handle the irregular distribution of sensors' spatial location. In this work, a novel graph-based convolution for imitating the meteorological flows is proposed to capture the local spatial patterns. Based on the assumption of smoothness of location-characterized patterns, we propose conditional local convolution whose shared kernel on nodes' local space is approximated by feedforward networks, with local representations of coordinate obtained by horizon maps into cylindrical-tangent space as its input. The established united standard of local coordinate system preserves the orientation on geography. We further propose the distance and orientation scaling terms to reduce the impacts of irregular spatial distribution. The convolution is embedded in a Recurrent Neural Network architecture to model the temporal dynamics, leading to the Conditional Local Convolution Recurrent Network (CLCRN). Our model is evaluated on real-world weather benchmark datasets, achieving state-of-the-art performance with obvious improvements. We conduct further analysis on local pattern visualization, model's framework choice, advantages of horizon maps and etc.
Conventional entity typing approaches are based on independent classification paradigms, which make them difficult to recognize inter-dependent, long-tailed and fine-grained entity types. In this paper, we argue that the implicitly entailed extrinsic and intrinsic dependencies between labels can provide critical knowledge to tackle the above challenges. To this end, we propose \emph{Label Reasoning Network(LRN)}, which sequentially reasons fine-grained entity labels by discovering and exploiting label dependencies knowledge entailed in the data. Specifically, LRN utilizes an auto-regressive network to conduct deductive reasoning and a bipartite attribute graph to conduct inductive reasoning between labels, which can effectively model, learn and reason complex label dependencies in a sequence-to-set, end-to-end manner. Experiments show that LRN achieves the state-of-the-art performance on standard ultra fine-grained entity typing benchmarks, and can also resolve the long tail label problem effectively.
Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this work, we aim to improve the cross-domain robustness of object detection. We tackle the domain shift on two levels: 1) the image-level shift, such as image style, illumination, etc, and 2) the instance-level shift, such as object appearance, size, etc. We build our approach based on the recent state-of-the-art Faster R-CNN model, and design two domain adaptation components, on image level and instance level, to reduce the domain discrepancy. The two domain adaptation components are based on H-divergence theory, and are implemented by learning a domain classifier in adversarial training manner. The domain classifiers on different levels are further reinforced with a consistency regularization to learn a domain-invariant region proposal network (RPN) in the Faster R-CNN model. We evaluate our newly proposed approach using multiple datasets including Cityscapes, KITTI, SIM10K, etc. The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191