Hierarchical Text Classification (HTC), which aims to predict text labels organized in hierarchical space, is a significant task lacking in investigation in natural language processing. Existing methods usually encode the entire hierarchical structure and fail to construct a robust label-dependent model, making it hard to make accurate predictions on sparse lower-level labels and achieving low Macro-F1. In this paper, we propose a novel PAMM-HiA-T5 model for HTC: a hierarchy-aware T5 model with path-adaptive mask mechanism that not only builds the knowledge of upper-level labels into low-level ones but also introduces path dependency information in label prediction. Specifically, we generate a multi-level sequential label structure to exploit hierarchical dependency across different levels with Breadth-First Search (BFS) and T5 model. To further improve label dependency prediction within each path, we then propose an original path-adaptive mask mechanism (PAMM) to identify the label's path information, eliminating sources of noises from other paths. Comprehensive experiments on three benchmark datasets show that our novel PAMM-HiA-T5 model greatly outperforms all state-of-the-art HTC approaches especially in Macro-F1. The ablation studies show that the improvements mainly come from our innovative approach instead of T5.
In this paper, we investigate the blind channel estimation problem for MIMO systems under Rayleigh fading channel. Conventional MIMO communication techniques require transmitting a considerable amount of training symbols as pilots in each data block to obtain the channel state information (CSI) such that the transmitted signals can be successfully recovered. However, the pilot overhead and contamination become a bottleneck for the practical application of MIMO systems with the increase of the number of antennas. To overcome this obstacle, we propose a blind channel estimation framework, where we introduce an auxiliary posterior distribution of CSI and the transmitted signals given the received signals to derive a lower bound to the intractable likelihood function of the received signal. Meanwhile, we generate this auxiliary distribution by a neural network based variational inference framework, which is trained by maximizing the lower bound. The optimal auxiliary distribution which approaches real prior distribution is then leveraged to obtain the maximum a posterior (MAP) estimation of channel matrix and transmitted data. The simulation results demonstrate that the performance of the proposed blind channel estimation method closely approaches that of the conventional pilot-aided methods in terms of the channel estimation error and symbol error rate (SER) of the detected signals even without the help of pilots.
Multi-phase computed tomography (CT) images provide crucial complementary information for accurate liver tumor segmentation (LiTS). State-of-the-art multi-phase LiTS methods usually fused cross-phase features through phase-weighted summation or channel-attention based concatenation. However, these methods ignored the spatial (pixel-wise) relationships between different phases, hence leading to insufficient feature integration. In addition, the performance of existing methods remains subject to the uncertainty in segmentation, which is particularly acute in tumor boundary regions. In this work, we propose a novel LiTS method to adequately aggregate multi-phase information and refine uncertain region segmentation. To this end, we introduce a spatial aggregation module (SAM), which encourages per-pixel interactions between different phases, to make full use of cross-phase information. Moreover, we devise an uncertain region inpainting module (URIM) to refine uncertain pixels using neighboring discriminative features. Experiments on an in-house multi-phase CT dataset of focal liver lesions (MPCT-FLLs) demonstrate that our method achieves promising liver tumor segmentation and outperforms state-of-the-arts.
Numerous visio-linguistic (V+L) representation learning methods have been developed, yet existing datasets do not evaluate the extent to which they represent visual and linguistic concepts in a unified space. Inspired by the crosslingual transfer and psycholinguistics literature, we propose a novel evaluation setting for V+L models: zero-shot cross-modal transfer. Existing V+L benchmarks also often report global accuracy scores on the entire dataset, rendering it difficult to pinpoint the specific reasoning tasks that models fail and succeed at. To address this issue and enable the evaluation of cross-modal transfer, we present TraVLR, a synthetic dataset comprising four V+L reasoning tasks. Each example encodes the scene bimodally such that either modality can be dropped during training/testing with no loss of relevant information. TraVLR's training and testing distributions are also constrained along task-relevant dimensions, enabling the evaluation of out-of-distribution generalisation. We evaluate four state-of-the-art V+L models and find that although they perform well on the test set from the same modality, all models fail to transfer cross-modally and have limited success accommodating the addition or deletion of one modality. In alignment with prior work, we also find these models to require large amounts of data to learn simple spatial relationships. We release TraVLR as an open challenge for the research community.
Motivated by privacy issues caused by inference attacks on user activities in the packet sizes and timing information of Internet of Things (IoT) network traffic, we establish a rigorous event-level differential privacy (DP) model on infinite packet streams. We propose a memoryless traffic shaping mechanism satisfying a first-come-first-served queuing discipline that outputs traffic dependent on the input using a DP mechanism. We show that in special cases the proposed mechanism recovers existing shapers which standardize the output independently from the input. To find the optimal shapers for given levels of privacy and transmission efficiency, we formulate the constrained problem of minimizing the expected delay per packet and propose using the expected queue size across time as a proxy. We further show that the constrained minimization is a convex program. We demonstrate the effect of shapers on both synthetic data and packet traces from actual IoT devices. The experimental results reveal inherent privacy-overhead tradeoffs: more shaping overhead provides better privacy protection. Under the same privacy level, there naturally exists a tradeoff between dummy traffic and delay. When dealing with heavier or less bursty input traffic, all shapers become more overhead-efficient. We also show that increased traffic from a larger number of IoT devices makes guaranteeing event-level privacy easier. The DP shaper offers tunable privacy that is invariant with the change in the input traffic distribution and has an advantage in handling burstiness over traffic-independent shapers. This approach well accommodates heterogeneous network conditions and enables users to adapt to their privacy/overhead demands.
Recently, deep-learning-based super-resolution methods have achieved excellent performances, but mainly focus on training a single generalized deep network by feeding numerous samples. Yet intuitively, each image has its representation, and is expected to acquire an adaptive model. For this issue, we propose a novel image-specific convolutional kernel modulation (IKM) by exploiting the global contextual information of image or feature to generate an attention weight for adaptively modulating the convolutional kernels, which outperforms the vanilla convolution and several existing attention mechanisms while embedding into the state-of-the-art architectures without any additional parameters. Particularly, to optimize our IKM in mini-batch training, we introduce an image-specific optimization (IsO) algorithm, which is more effective than the conventional mini-batch SGD optimization. Furthermore, we investigate the effect of IKM on the state-of-the-art architectures and exploit a new backbone with U-style residual learning and hourglass dense block learning, terms U-Hourglass Dense Network (U-HDN), which is an appropriate architecture to utmost improve the effectiveness of IKM theoretically and experimentally. Extensive experiments on single image super-resolution show that the proposed methods achieve superior performances over state-of-the-art methods. Code is available at github.com/YuanfeiHuang/IKM.
The multi-task learning (MTL) paradigm can be traced back to an early paper of Caruana (1997) in which it was argued that data from multiple tasks can be used with the aim to obtain a better performance over learning each task independently. A solution of MTL with conflicting objectives requires modelling the trade-off among them which is generally beyond what a straight linear combination can achieve. A theoretically principled and computationally effective strategy is finding solutions which are not dominated by others as it is addressed in the Pareto analysis. Multi-objective optimization problems arising in the multi-task learning context have specific features and require adhoc methods. The analysis of these features and the proposal of a new computational approach represent the focus of this work. Multi-objective evolutionary algorithms (MOEAs) can easily include the concept of dominance and therefore the Pareto analysis. The major drawback of MOEAs is a low sample efficiency with respect to function evaluations. The key reason for this drawback is that most of the evolutionary approaches do not use models for approximating the objective function. Bayesian Optimization takes a radically different approach based on a surrogate model, such as a Gaussian Process. In this thesis the solutions in the Input Space are represented as probability distributions encapsulating the knowledge contained in the function evaluations. In this space of probability distributions, endowed with the metric given by the Wasserstein distance, a new algorithm MOEA/WST can be designed in which the model is not directly on the objective function but in an intermediate Information Space where the objects from the input space are mapped into histograms. Computational results show that the sample efficiency and the quality of the Pareto set provided by MOEA/WST are significantly better than in the standard MOEA.
OpenStreetMap (OSM) is currently the richest publicly available information source on geographic entities (e.g., buildings and roads) worldwide. However, using OSM entities in machine learning models and other applications is challenging due to the large scale of OSM, the extreme heterogeneity of entity annotations, and a lack of a well-defined ontology to describe entity semantics and properties. This paper presents GeoVectors - a unique, comprehensive world-scale linked open corpus of OSM entity embeddings covering the entire OSM dataset and providing latent representations of over 980 million geographic entities in 180 countries. The GeoVectors corpus captures semantic and geographic dimensions of OSM entities and makes these entities directly accessible to machine learning algorithms and semantic applications. We create a semantic description of the GeoVectors corpus, including identity links to the Wikidata and DBpedia knowledge graphs to supply context information. Furthermore, we provide a SPARQL endpoint - a semantic interface that offers direct access to the semantic and latent representations of geographic entities in OSM.
With the popularity of Transformer architectures in computer vision, the research focus has shifted towards developing computationally efficient designs. Window-based local attention is one of the major techniques being adopted in recent works. These methods begin with very small patch size and small embedding dimensions and then perform strided convolution (patch merging) in order to reduce the feature map size and increase embedding dimensions, hence, forming a pyramidal Convolutional Neural Network (CNN) like design. In this work, we investigate local and global information modelling in transformers by presenting a novel isotropic architecture that adopts local windows and special tokens, called Super tokens, for self-attention. Specifically, a single Super token is assigned to each image window which captures the rich local details for that window. These tokens are then employed for cross-window communication and global representation learning. Hence, most of the learning is independent of the image patches $(N)$ in the higher layers, and the class embedding is learned solely based on the Super tokens $(N/M^2)$ where $M^2$ is the window size. In standard image classification on Imagenet-1K, the proposed Super tokens based transformer (STT-S25) achieves 83.5\% accuracy which is equivalent to Swin transformer (Swin-B) with circa half the number of parameters (49M) and double the inference time throughput. The proposed Super token transformer offers a lightweight and promising backbone for visual recognition tasks.
Deep neural networks (DNNs) have been employed for designing wireless networks in many aspects, such as transceiver optimization, resource allocation, and information prediction. Existing works either use fully-connected DNN or the DNNs with specific structures that are designed in other domains. In this paper, we show that a priori information widely existed in wireless tasks is permutation invariant. For these tasks, we propose a DNN with special structure, where the weight matrices between layers of the DNN only consist of two smaller sub-matrices. By such way of parameter sharing, the number of model parameters reduces, giving rise to low sample and computational complexity for training a DNN. We take predictive resource allocation as an example to show how the designed DNN can be applied for learning the optimal policy with unsupervised learning. Simulations results validate our analysis and show dramatic gain of the proposed structure in terms of reducing training complexity.