D high-density NAND flash has a limited voltage window that narrows page read margins, making it vulnerable to read disturbance and triggering Read Refresh Operations (RROs). Existing methods ignore repeated voltage states caused by invalid pages on the same wordline, failing to fully utilize the voltage range. This paper proposes an Invalid Page-Aware Refresh (IPAR) scheme to achieve high-performance 3D highdensity NAND flash memory. First, IPAR merges repeated voltage states through reprogramming to widen valid page read margins and improve read endurance thresholds. Moreover, IPAR further adopts a page-level allocation strategy that contains two operations: hot-write data is placed on high-latency pages to allow more reprogramming operations, while hot-read data is allocated to low-latency pages of reprogrammed blocks, effectively mitigating read disturbance and reducing migration overhead. Trace-driven simulations based on FEMU show that IPAR reduces RROs triggers by 38.91%, write amplification by 48.08%, and average response time by 16.93% compared to baseline.

To analyze and process graph data, researchers have proposed Graph Neural Network (GNN) models. In this paper, we focus on methods for boosting the performance of existing GNN models and propose GraphHI, a GNN framework that integrates Hidden Insights to enhance the performance of a given GNN model. We propose to utilize both inter-model and intra-model hidden insights. The inter-model hidden insights encompass the embedding vectors and logit vectors derived from other pretrained models using the same graph data. The intra-model hidden insights incorporate the embedding vectors of other nodes from the same GNN model. To optimize the suitability of hidden insights for GNN model training, we conduct a theoretical analysis of the influence of various forms of the transformed logits and the parameter$T$in the data transformation function. Based on this analysis, a method for setting dynamic personalized parameters in the data transformation is proposed, which is tailored to the current state of each node in the GNN model. To integrate multiple sources of hidden insights, we propose ALC, an algorithm that dynamically sets appropriate combination coefficients for various loss terms. The experimental results show that GraphHI can boost the performance of GNN models using different pretrained models in four different tasks.

CTR(click through rate) model has played an important role in modern recommendation systems. Most of the recommendation models in industrial scenario are trained by TensorFlow. However, we observed that, TFRecord, the native k-v data format in TensorFlow, is not the best choice for CTR training. Those keys take up to 54% of the storage space in TFRecord formatted training data. To overcome this, we introduce Apache Parquet, a column-oriented data format, into CTR tasks to improve spatial efficiency. Besides, to use in production environment, we further give some high performance implementations of Parquet training scheme. Firstly, GPU data preprocessing method is adopted in replace of original Spark based solution to generate Parquet training data and accelerate data preprocessing. Secondly, we modify data loader in TensorFlow to consume the Parquet training data with high efficiency. Experimental results show that, the size of preprocessed Criteo dataset is 95.29% smaller in comparison to TFRecord and the data preprocessing time also reduces 99.6%. Without any model performance damage, we speed up the training process by 1.45x. Our scheme has applied to our internal business and has obtained similar performance benefits.

As one of the largest B2C e-commerce platforms in China, JD.com also powers a leading advertising system, serving millions of advertisers with fingertip connection to hundreds of millions of customers. In our system, as well as most e-commerce scenarios, ads are displayed with images. This makes visual-aware Click Through Rate (CTR) prediction of crucial importance to both business effectiveness and user experience. Existing algorithms usually extract visual features using off-the-shelf Convolutional Neural Networks (CNNs) and late fuse the visual and non-visual features for the finally predicted CTR. Despite being extensively studied, this field still face two key challenges. First, although encouraging progress has been made in offline studies, applying CNNs in real systems remains non-trivial, due to the strict requirements for efficient end-to-end training and low-latency online serving. Second, the off-the-shelf CNNs and late fusion architectures are suboptimal. Specifically, off-the-shelf CNNs were designed for classification thus never take categories as input features. While in e-commerce, categories are precisely labeled and contain abundant visual priors that will help the visual modeling. Unaware of the ad category, these CNNs may extract some unnecessary category-unrelated features, wasting CNN's limited expression ability. To overcome the two challenges, we propose Category-specific CNN (CSCNN) specially for CTR prediction. CSCNN early incorporates the category knowledge with a light-weighted attention-module on each convolutional layer. This enables CSCNN to extract expressive category-specific visual patterns that benefit the CTR prediction. Offline experiments on benchmark and a 10 billion scale real production dataset from JD, together with an Online A/B test show that CSCNN outperforms all compared state-of-the-art algorithms. We also build a highly efficient infrastructure to accomplish end-to-end training with CNN on the 10 billion scale real production dataset within 24 hours, and meet the low latency requirements of online system (20ms on CPU). CSCNN is now deployed in the search advertising system of JD, serving the main traffic of hundreds of millions of active users.

Due to the specificity of space borne synthetic aperture radar (SAR) sensors, the stereoscopic pair can only be generated in across-track direction. However, the stereo can also be generated with triplet images when SAR system can span large values of incidence angle, such as Radarsat, TerraSAR and CosmoSky-Med. In this paper, the triplet stereo was introduced to high-resolution Radarsat-2 data for generating DTM. For this study, three high-resolution images from Radarsat-2 were acquired with 31°, 38° and 47° incidence angles over a rolling topography of north of Quebec City, Canada. Two main steps of generation of DTM, including the geometry for 3-D modeling and the radiometry for image matching were carried out. For 3-D modeling, one deterministic model, Tontin's 3-D Radargrammetric Model, was applied to mono/stereo/triplet Radarsat-2 data. For image matching, a NCC algorithm was used. The differential GPS points and LiDAR products were used as reference data. Preliminaries results of triplet stereo with simulated SAR HR data of the new Canadian Radar Constellation Mission will be presented at IGARSSS 2012.

High accurate airborne Light Detection and Range (LiDAR) is widely accepted as one kind of survey data sources. However, with the LiDAR products including Digital Elevation Model (DEM), Digital Surface Model (DSM) and intensity image, land use classifications and feature extractions were generally combined with optical images including satellite images or aerial photos using relative segmentations and feature extraction algorithms. In this paper, a multi-window texture classification and object- oriented feature extraction method is proposed using only airborne LiDAR products. Based on the experimental analysis and accuracy statistics, it is an efficient attempt in land cover classification with airborne LiDAR products.