Reinforcement learning from human feedback (RLHF) is a crucial technique in aligning large language models (LLMs) with human preferences, ensuring these LLMs behave in beneficial and comprehensible ways to users. However, a longstanding challenge in human alignment techniques based on reinforcement learning lies in their inherent complexity and difficulty in training. To address this challenge, we present a simple yet effective Contrastive Learning Framework for Human Alignment (CLHA) to align LLMs with human preferences directly. CLHA employs a novel rescoring strategy to evaluate the noise within the data by considering its inherent quality and dynamically adjusting the training process. Simultaneously, CLHA utilizes pairwise contrastive loss and adaptive supervised fine-tuning loss to adaptively modify the likelihood of generating responses, ensuring enhanced alignment with human preferences. Using advanced methods, CLHA surpasses other algorithms, showcasing superior performance in terms of reward model scores, automatic evaluations, and human assessments on the widely used ``Helpful and Harmless'' dataset.
The prevalence of large-scale graphs poses great challenges in time and storage for training and deploying graph neural networks (GNNs). Several recent works have explored solutions for pruning the large original graph into a small and highly-informative one, such that training and inference on the pruned and large graphs have comparable performance. Although empirically effective, current researches focus on static or non-temporal graphs, which are not directly applicable to dynamic scenarios. In addition, they require labels as ground truth to learn the informative structure, limiting their applicability to new problem domains where labels are hard to obtain. To solve the dilemma, we propose and study the problem of unsupervised graph pruning on dynamic graphs. We approach the problem by our proposed STEP, a self-supervised temporal pruning framework that learns to remove potentially redundant edges from input dynamic graphs. From a technical and industrial viewpoint, our method overcomes the trade-offs between the performance and the time & memory overheads. Our results on three real-world datasets demonstrate the advantages on improving the efficacy, robustness, and efficiency of GNNs on dynamic node classification tasks. Most notably, STEP is able to prune more than 50% of edges on a million-scale industrial graph Alipay (7M nodes, 21M edges) while approximating up to 98% of the original performance. Code is available at https://github.com/EdisonLeeeee/STEP.
We present masked graph autoencoder (MaskGAE), a self-supervised learning framework for graph-structured data. Different from previous graph autoencoders (GAEs), MaskGAE adopts masked graph modeling (MGM) as a principled pretext task: masking a portion of edges and attempting to reconstruct the missing part with partially visible, unmasked graph structure. To understand whether MGM can help GAEs learn better representations, we provide both theoretical and empirical evidence to justify the benefits of this pretext task. Theoretically, we establish the connections between GAEs and contrastive learning, showing that MGM significantly improves the self-supervised learning scheme of GAEs. Empirically, we conduct extensive experiments on a number of benchmark datasets, demonstrating the superiority of MaskGAE over several state-of-the-arts on both link prediction and node classification tasks. Our code is publicly available at \url{https://github.com/EdisonLeeeee/MaskGAE}.
In this paper, we study to employ geographic information to address the blockage problem of air-to-ground links between UAV and terrestrial nodes. In particular, a UAV relay is deployed to establish communication links from a ground base station to multiple ground users. To improve communication capacity, we first model the blockage effect caused by buildings according to the three-dimensional (3-D) geographic information. Then, an optimization problem is formulated to maximize the minimum capacity among users by jointly optimizing the 3-D position and power allocation of the UAV relay, under the constraints of link capacity, maximum transmit power, and blockage. To solve this complex non-convex problem, a two-loop optimization framework is developed based on Lagrangian relaxation. The outer-loop aims to obtain proper Lagrangian multipliers to ensure the solution of the Lagrangian problem converge to the tightest upper bound on the original problem. The inner-loop solves the Lagrangian problem by applying the block coordinate descent (BCD) and successive convex approximation (SCA) techniques, where UAV 3-D positioning and power allocation are alternately optimized in each iteration. Simulation results confirm that the proposed solution significantly outperforms two benchmark schemes and achieves a performance close to the upper bound on the UAV relay system.
Most modern Multi-Object Tracking (MOT) systems typically apply REID-based paradigm to hold a balance between computational efficiency and performance. In the past few years, numerous attempts have been made to perfect the systems. Although they presented favorable performance, they were constrained to track specified category. Drawing on the ideas of few shot method, we pioneered a new multi-target tracking system, named MOTS, which is based on metrics but not limited to track specific category. It contains two stages in series: In the first stage, we design the self-Adaptive-matching module to perform simple targets matching, which can complete 88.76% assignments without sacrificing performance on MOT16 training set. In the second stage, a Fine-match Network was carefully designed for unmatched targets. With a newly built TRACK-REID data-set, the Fine-match Network can perform matching of 31 category targets, even generalizes to unseen categories.
Computer vision algorithms are being implemented across a breadth of industries to enable technological innovations. In this paper, we study the problem of computer vision based customer tracking in retail industry. To this end, we introduce a dataset collected from a camera in an office environment where participants mimic various behaviors of customers in a supermarket. In addition, we describe an illustrative example of the use of this dataset for tracking participants based on a head tracking model in an effort to minimize errors due to occlusion. Furthermore, we propose a model for recognizing customers and staff based on their movement patterns. The model is evaluated using a real-world dataset collected in a supermarket over a 24-hour period that achieves 98\% accuracy during training and 93\% accuracy during evaluation.
The task of crowd counting in varying density scenes is an extremely difficult challenge due to large scale variations. In this paper, we propose a novel dual path multi-scale fusion network architecture with attention mechanism named SFANet that can perform accurate count estimation as well as present high-resolution density maps for highly congested crowd scenes. The proposed SFANet contains two main components: a VGG backbone convolutional neural network (CNN) as the front-end feature map extractor and a dual path multi-scale fusion networks as the back-end to generate density map. These dual path multi-scale fusion networks have the same structure, one path is responsible for generating attention map by highlighting crowd regions in images, the other path is responsible for fusing multi-scale features as well as attention map to generate the final high-quality high-resolution density maps. SFANet can be easily trained in an end-to-end way by dual path joint training. We have evaluated our method on four crowd counting datasets (ShanghaiTech, UCF CC 50, UCSD and UCF-QRNF). The results demonstrate that with attention mechanism and multi-scale feature fusion, the proposed SFANet achieves the best performance on all these datasets and generates better quality density maps compared with other state-of-the-art approaches.
In this paper, we introduce our submissions for the tasks of trimmed activity recognition (Kinetics) and trimmed event recognition (Moments in Time) for Activitynet Challenge 2018. In the two tasks, non-local neural networks and temporal segment networks are implemented as our base models. Multi-modal cues such as RGB image, optical flow and acoustic signal have also been used in our method. We also propose new non-local-based models for further improvement on the recognition accuracy. The final submissions after ensembling the models achieve 83.5% top-1 accuracy and 96.8% top-5 accuracy on the Kinetics validation set, 35.81% top-1 accuracy and 62.59% top-5 accuracy on the MIT validation set.
The Three Gorges Dam, a massive cross-century project spans the Yangtze River by the town of Sandouping, located in Yichang, Hubei province, China, was built to provide great power, improve the River shipping, control floods in the upper reaches of the Yangtze River, and increase the dry season flow in the middle and lower reaches of the Yangtze River. Benefits are enormous and comprehensive. However, the social and environmental impacts are also immense and far-reaching to its surrounding areas. Mapping land use /land cover changed (LUCC) is critical for tracking the impacts. Remote sensing has been proved to be an effective way to map and monitor land use change in real time and in large areas such as the Three Gorges Reservoir Area(TGRA) by using pixel based or oriented based classifier in different resolution. In this paper, we first test the state of the art semantic segmentation deep learning classifiers for LUCC mapping with 7 categories in the TGRA area with rapideye 5m resolution data. The topographic information was also added for better accuracy in mountain area. By compared with the pixel-based classifier, the semantic segmentation deep learning method has better accuracy and robustness at 5m resolution level.