Link prediction is a fundamental task for graph analysis with important applications on the Web, such as social network analysis and recommendation systems, \etc\ Modern graph link prediction methods often employ a contrastive approach to learn robust node representations, where negative sampling is pivotal. Typical negative sampling methods aim to retrieve hard examples based on either predefined heuristics or automatic adversarial approaches, which might be inflexible or difficult to control. Furthermore, in the context of link prediction, most previous methods sample negative nodes from existing substructures of the graph, missing out on potentially more optimal samples in the latent space. To address these issues, we investigate a novel strategy of multi-level negative sampling that enables negative node generation with flexible and controllable "hardness'' levels from the latent space. Our method, called Conditional Diffusion-based Multi-level Negative Sampling (DMNS), leverages the Markov chain property of diffusion models to generate negative nodes in multiple levels of variable hardness and reconcile them for effective graph link prediction. We further demonstrate that DMNS follows the sub-linear positivity principle for robust negative sampling. Extensive experiments on several benchmark datasets demonstrate the effectiveness of DMNS.

Conventional graph neural networks (GNNs) are often confronted with fairness issues that may stem from their input, including node attributes and neighbors surrounding a node. While several recent approaches have been proposed to eliminate the bias rooted in sensitive attributes, they ignore the other key input of GNNs, namely the neighbors of a node, which can introduce bias since GNNs hinge on neighborhood structures to generate node representations. In particular, the varying neighborhood structures across nodes, manifesting themselves in drastically different node degrees, give rise to the diverse behaviors of nodes and biased outcomes. In this paper, we first define and generalize the degree bias using a generalized definition of node degree as a manifestation and quantification of different multi-hop structures around different nodes. To address the bias in the context of node classification, we propose a novel GNN framework called Generalized Degree Fairness-centric Graph Neural Network (DegFairGNN). Specifically, in each GNN layer, we employ a learnable debiasing function to generate debiasing contexts, which modulate the layer-wise neighborhood aggregation to eliminate the degree bias originating from the diverse degrees among nodes. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our model on both accuracy and fairness metrics.

On graph data, the multitude of node or edge types gives rise to heterogeneous information networks (HINs). To preserve the heterogeneous semantics on HINs, the rich node/edge types become a cornerstone of HIN representation learning. However, in real-world scenarios, type information is often noisy, missing or inaccessible. Assuming no type information is given, we define a so-called latent heterogeneous graph (LHG), which carries latent heterogeneous semantics as the node/edge types cannot be observed. In this paper, we study the challenging and unexplored problem of link prediction on an LHG. As existing approaches depend heavily on type-based information, they are suboptimal or even inapplicable on LHGs. To address the absence of type information, we propose a model named LHGNN, based on the novel idea of semantic embedding at node and path levels, to capture latent semantics on and between nodes. We further design a personalization function to modulate the heterogeneous contexts conditioned on their latent semantics w.r.t. the target node, to enable finer-grained aggregation. Finally, we conduct extensive experiments on four benchmark datasets, and demonstrate the superior performance of LHGNN.

The prevalence of graph structures in real-world scenarios enables important tasks such as node classification and link prediction. Graphs in many domains follow a long-tailed distribution in their node degrees, i.e., a significant fraction of nodes are tail nodes with a small degree. Although recent graph neural networks (GNNs) can learn powerful node representations, they treat all nodes uniformly and are not tailored to the large group of tail nodes. In particular, there is limited structural information (i.e., links) on tail nodes, resulting in inferior performance. Toward robust tail node embedding, in this paper we propose a novel graph neural network called Tail-GNN. It hinges on the novel concept of transferable neighborhood translation, to model the variable ties between a target node and its neighbors. On one hand, Tail-GNN learns a neighborhood translation from the structurally rich head nodes (i.e., high-degree nodes), which can be further transferred to the structurally limited tail nodes to enhance their representations. On the other hand, the ties with the neighbors are variable across different parts of the graph, and a global neighborhood translation is inflexible. Thus, we devise a node-wise adaptation to localize the global translation w.r.t. each node. Extensive experiments on five benchmark datasets demonstrate that our proposed Tail-GNN significantly outperforms the state-of-the-art baselines.

Recent successes in Generative Adversarial Networks (GAN) have affirmed the importance of using more data in GAN training. Yet it is expensive to collect data in many domains such as medical applications. Data Augmentation (DA) has been applied in these applications. In this work, we first argue that the classical DA approach could mislead the generator to learn the distribution of the augmented data, which could be different from that of the original data. We then propose a principled framework, termed Data Augmentation Optimized for GAN (DAG), to enable the use of augmented data in GAN training to improve the learning of the original distribution. We provide theoretical analysis to show that using our proposed DAG aligns with the original GAN in minimizing the Jensen-Shannon (JS) divergence between the original distribution and model distribution. Importantly, the proposed DAG effectively leverages the augmented data to improve the learning of discriminator and generator. We conduct experiments to apply DAG to different GAN models: unconditional GAN, conditional GAN, self-supervised GAN and CycleGAN using datasets of natural images and medical images. The results show that DAG achieves consistent and considerable improvements across these models. Furthermore, when DAG is used in some GAN models, the system establishes state-of-the-art Fréchet Inception Distance (FID) scores. Our code is available (https://github.com/tntrung/dag-gans).

This paper presents a low power high linearity transmitter front-end for 900 MHz Zigbee applications based on 0.18 /spl mu/m CMOS technology. The direct up-conversion is implemented by passive mixer which dissipates no DC current. Two stage driver amplifiers provide high enough gain as well as high linearity to drive high power signal to 50/spl Omega/ antenna while consuming small amount of current. Measurement shows 11.5 dB overall transmitter gain, 3 dBm output P1dB while dissipating 1.8mA DC current from 1.8 V supply.

This paper presents a new configuration for linear MOS operation transconductance amplifier (OTA) based on a standard 0.25 /spl mu/m CMOS technology. The proposed circuit combines two previously reported linearization techniques: source degeneration using MOS transistor and class AB linearization. Measured results show that the proposed circuit provides rail-to-rail differential input range. Total harmonic distortion of the proposed circuit is -60 dB at 5 MHz for 0.6-Vpp differential input voltage while dissipating only 25 /spl mu/W from 1.25 V supply.

This paper presents a sub-mA, low-noise, high-gain CMOS low noise amplifier (LNA) for 2.4-GHz band applications based on 0.18 /spl mu/m CMOS technology. Low-noise under power-constrained can be achieved by using an inductive cascode degeneration amplifier with an extra gate-source capacitor. Gain enhancement can be obtained by using capacitive feedback at the cascode transistor. Measurements show 16 dB gain, 1.8 dB NF, -10 dBm IIP3 while dissipating only 0.5 mA from 1.5 V supply.

A CMOS voltage-to-current converter with exponential characteristic is presented in this paper. The concept of Taylor series expansion is used for realizing the exponential characteristic. The proposed exponential V-I converter is composed of a current-to-current squarer and a linear V-I converter with the use of linearization technique. Based on a 0.25 µm CMOS process, simulations show a 23 dB of linear-output current range and the linearity within 20 dB with error less than ± 0.5dB is achieved. The total power consumption is below 0.2 mW with 1.25 V supply voltage. The proposed circuit can be used for the design of an extremely low-voltage low-power variable gain amplifier (VGA).