Online bidding and auction are crucial aspects of the online advertising industry. Conventionally, there is only one slot for ad display and most current studies focus on it. Nowadays, multi-slot display advertising is gradually becoming popular where many ads could be displayed in a list and shown as a whole to users. However, multi-slot display advertising leads to different cost-effectiveness. Advertisers have the incentive to adjust bid prices so as to win the most economical ad positions. In this study, we introduce bid shading into multi-slot display advertising for bid price adjustment with a Multi-task End-to-end Bid Shading(MEBS) method. We prove the optimality of our method theoretically and examine its performance experimentally. Through extensive offline and online experiments, we demonstrate the effectiveness and efficiency of our method, and we obtain a 7.01% lift in Gross Merchandise Volume, a 7.42% lift in Return on Investment, and a 3.26% lift in ad buy count.
In online advertising, advertisers participate in ad auctions to acquire ad opportunities, often by utilizing auto-bidding tools provided by demand-side platforms (DSPs). The current auto-bidding algorithms typically employ reinforcement learning (RL). However, due to safety concerns, most RL-based auto-bidding policies are trained in simulation, leading to a performance degradation when deployed in online environments. To narrow this gap, we can deploy multiple auto-bidding agents in parallel to collect a large interaction dataset. Offline RL algorithms can then be utilized to train a new policy. The trained policy can subsequently be deployed for further data collection, resulting in an iterative training framework, which we refer to as iterative offline RL. In this work, we identify the performance bottleneck of this iterative offline RL framework, which originates from the ineffective exploration and exploitation caused by the inherent conservatism of offline RL algorithms. To overcome this bottleneck, we propose Trajectory-wise Exploration and Exploitation (TEE), which introduces a novel data collecting and data utilization method for iterative offline RL from a trajectory perspective. Furthermore, to ensure the safety of online exploration while preserving the dataset quality for TEE, we propose Safe Exploration by Adaptive Action Selection (SEAS). Both offline experiments and real-world experiments on Alibaba display advertising platform demonstrate the effectiveness of our proposed method.
Existing methods for fine-tuning sparse LLMs often suffer from resource-intensive requirements and high retraining costs. Additionally, many fine-tuning methods often rely on approximations or heuristic optimization strategies, which may lead to suboptimal solutions. To address these issues, we propose an efficient and fast framework for fine-tuning sparse LLMs based on minimizing reconstruction error. Our approach involves sampling a small dataset for calibration and utilizing backpropagation to iteratively optimize block-wise reconstruction error, on a block-by-block basis, aiming for optimal solutions. Extensive experiments on various benchmarks consistently demonstrate the superiority of our method over other baselines. For instance, on the Wikitext2 dataset with LlamaV1-7B at 70% sparsity, our proposed EBFT achieves a perplexity of 16.88, surpassing the state-of-the-art DSnoT with a perplexity of 75.14. Moreover, with a structured sparsity ratio of 26\%, EBFT achieves a perplexity of 16.27, outperforming LoRA (perplexity 16.44). Furthermore, the fine-tuning process of EBFT for LlamaV1-7B only takes approximately 30 minutes, and the entire framework can be executed on a single 16GB GPU. The source code is available at https://github.com/sunggo/EBFT.
In this paper, we focus on a realistic yet challenging task, Single Domain Generalization Object Detection (S-DGOD), where only one source domain's data can be used for training object detectors, but have to generalize multiple distinct target domains. In S-DGOD, both high-capacity fitting and generalization abilities are needed due to the task's complexity. Differentiable Neural Architecture Search (NAS) is known for its high capacity for complex data fitting and we propose to leverage Differentiable NAS to solve S-DGOD. However, it may confront severe over-fitting issues due to the feature imbalance phenomenon, where parameters optimized by gradient descent are biased to learn from the easy-to-learn features, which are usually non-causal and spuriously correlated to ground truth labels, such as the features of background in object detection data. Consequently, this leads to serious performance degradation, especially in generalizing to unseen target domains with huge domain gaps between the source domain and target domains. To address this issue, we propose the Generalizable loss (G-loss), which is an OoD-aware objective, preventing NAS from over-fitting by using gradient descent to optimize parameters not only on a subset of easy-to-learn features but also the remaining predictive features for generalization, and the overall framework is named G-NAS. Experimental results on the S-DGOD urban-scene datasets demonstrate that the proposed G-NAS achieves SOTA performance compared to baseline methods. Codes are available at https://github.com/wufan-cse/G-NAS.
Controlling the shape of deformable linear objects using robots and constraints provided by environmental fixtures has diverse industrial applications. In order to establish robust contacts with these fixtures, accurate estimation of the contact state is essential for preventing and rectifying potential anomalies. However, this task is challenging due to the small sizes of fixtures, the requirement for real-time performances, and the infinite degrees of freedom of the deformable linear objects. In this paper, we propose a real-time approach for estimating both contact establishment and subsequent changes by leveraging the dependency between the applied and detected contact force on the deformable linear objects. We seamlessly integrate this method into the robot control loop and achieve an adaptive shape control framework which avoids, detects and corrects anomalies automatically. Real-world experiments validate the robustness and effectiveness of our contact estimation approach across various scenarios, significantly increasing the success rate of shape control processes.
The age and mass of red giants are essential for understanding the structure and evolution of the Milky Way. Traditional isochrone methods for these estimations are inherently limited due to overlapping isochrones in the Hertzsprung-Russell diagram, while asteroseismology, though more precise, requires high-precision, long-term observations. In response to these challenges, we developed a novel framework, Spectral Transformer (SPT), to predict the age and mass of red giants aligned with asteroseismology from their spectra. A key component of SPT, the Multi-head Hadamard Self-Attention mechanism, designed specifically for spectra, can capture complex relationships across different wavelength. Further, we introduced a Mahalanobis distance-based loss function to address scale imbalance and interaction mode loss, and incorporated Monte Carlo dropout for quantitative analysis of prediction uncertainty.Trained and tested on 3,880 red giant spectra from LAMOST, the SPT achieved remarkable age and mass estimations with average percentage errors of 17.64% and 6.61%, respectively, and provided uncertainties for each corresponding prediction. The results significantly outperform those of traditional machine learning algorithms and demonstrate a high level of consistency with asteroseismology methods and isochrone fitting techniques. In the future, our work will leverage datasets from the Chinese Space Station Telescope and the Large Synoptic Survey Telescope to enhance the precision of the model and broaden its applicability in the field of astronomy and astrophysics.
Pervasive mobile AI applications primarily employ one of the two learning paradigms: cloud-based learning (with powerful large models) or on-device learning (with lightweight small models). Despite their own advantages, neither paradigm can effectively handle dynamic edge environments with frequent data distribution shifts and on-device resource fluctuations, inevitably suffering from performance degradation. In this paper, we propose ECLM, an edge-cloud collaborative learning framework for rapid model adaptation for dynamic edge environments. We first propose a novel block-level model decomposition design to decompose the original large cloud model into multiple combinable modules. By flexibly combining a subset of the modules, this design enables the derivation of compact, task-specific sub-models for heterogeneous edge devices from the large cloud model, and the seamless integration of new knowledge learned on these devices into the cloud model periodically. As such, ECLM ensures that the cloud model always provides up-to-date sub-models for edge devices. We further propose an end-to-end learning framework that incorporates the modular model design into an efficient model adaptation pipeline including an offline on-cloud model prototyping and training stage, and an online edge-cloud collaborative adaptation stage. Extensive experiments over various datasets demonstrate that ECLM significantly improves model performance (e.g., 18.89% accuracy increase) and resource efficiency (e.g., 7.12x communication cost reduction) in adapting models to dynamic edge environments by efficiently collaborating the edge and the cloud models.
Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to enhance the agent's generalization ability on unseen tasks. However, the context shift problem arises due to the distribution discrepancy between the contexts used for training (from the behavior policy) and testing (from the exploration policy). The context shift problem leads to incorrect task inference and further deteriorates the generalization ability of the meta-policy. Existing OMRL methods either overlook this problem or attempt to mitigate it with additional information. In this paper, we propose a novel approach called Context Shift Reduction for OMRL (CSRO) to address the context shift problem with only offline datasets. The key insight of CSRO is to minimize the influence of policy in context during both the meta-training and meta-test phases. During meta-training, we design a max-min mutual information representation learning mechanism to diminish the impact of the behavior policy on task representation. In the meta-test phase, we introduce the non-prior context collection strategy to reduce the effect of the exploration policy. Experimental results demonstrate that CSRO significantly reduces the context shift and improves the generalization ability, surpassing previous methods across various challenging domains.
In the field of multi-task reinforcement learning, the modular principle, which involves specializing functionalities into different modules and combining them appropriately, has been widely adopted as a promising approach to prevent the negative transfer problem that performance degradation due to conflicts between tasks. However, most of the existing multi-task RL methods only combine shared modules at the task level, ignoring that there may be conflicts within the task. In addition, these methods do not take into account that without constraints, some modules may learn similar functions, resulting in restricting the model's expressiveness and generalization capability of modular methods. In this paper, we propose the Contrastive Modules with Temporal Attention(CMTA) method to address these limitations. CMTA constrains the modules to be different from each other by contrastive learning and combining shared modules at a finer granularity than the task level with temporal attention, alleviating the negative transfer within the task and improving the generalization ability and the performance for multi-task RL. We conducted the experiment on Meta-World, a multi-task RL benchmark containing various robotics manipulation tasks. Experimental results show that CMTA outperforms learning each task individually for the first time and achieves substantial performance improvements over the baselines.
Positioned between pre-training and user deployment, aligning large language models (LLMs) through reinforcement learning (RL) has emerged as a prevailing strategy for training instruction following-models such as ChatGPT. In this work, we initiate the study of privacy-preserving alignment of LLMs through Differential Privacy (DP) in conjunction with RL. Following the influential work of Ziegler et al. (2020), we study two dominant paradigms: (i) alignment via RL without human in the loop (e.g., positive review generation) and (ii) alignment via RL from human feedback (RLHF) (e.g., summarization in a human-preferred way). We give a new DP framework to achieve alignment via RL, and prove its correctness. Our experimental results validate the effectiveness of our approach, offering competitive utility while ensuring strong privacy protections.