SIMGA: A Simple and Effective Heterophilous Graph Neural Network with Efficient Global Aggregation

Graph neural networks (GNNs) realize great success in graph learning but suffer from performance loss when meeting heterophily, i.e. neighboring nodes are dissimilar, due to their local and uniform aggregation. Existing attempts in incoorporating global aggregation for heterophilous GNNs usually require iteratively maintaining and updating full-graph information, which entails $\mathcal{O}(n^2)$ computation efficiency for a graph with $n$ nodes, leading to weak scalability to large graphs. In this paper, we propose SIMGA, a GNN structure integrating SimRank structural similarity measurement as global aggregation. The design of SIMGA is simple, yet it leads to promising results in both efficiency and effectiveness. The simplicity of SIMGA makes it the first heterophilous GNN model that can achieve a propagation efficiency near-linear to $n$. We theoretically demonstrate its effectiveness by treating SimRank as a new interpretation of GNN and prove that the aggregated node representation matrix has expected grouping effect. The performances of SIMGA are evaluated with 11 baselines on 12 benchmark datasets, usually achieving superior accuracy compared with the state-of-the-art models. Efficiency study reveals that SIMGA is up to 5$\times$ faster than the state-of-the-art method on the largest heterophily dataset pokec with over 30 million edges.

Dual Semantic Knowledge Composed Multimodal Dialog Systems

Textual response generation is an essential task for multimodal task-oriented dialog systems.Although existing studies have achieved fruitful progress, they still suffer from two critical limitations: 1) focusing on the attribute knowledge but ignoring the relation knowledge that can reveal the correlations between different entities and hence promote the response generation}, and 2) only conducting the cross-entropy loss based output-level supervision but lacking the representation-level regularization. To address these limitations, we devise a novel multimodal task-oriented dialog system (named MDS-S2). Specifically, MDS-S2 first simultaneously acquires the context related attribute and relation knowledge from the knowledge base, whereby the non-intuitive relation knowledge is extracted by the n-hop graph walk. Thereafter, considering that the attribute knowledge and relation knowledge can benefit the responding to different levels of questions, we design a multi-level knowledge composition module in MDS-S2 to obtain the latent composed response representation. Moreover, we devise a set of latent query variables to distill the semantic information from the composed response representation and the ground truth response representation, respectively, and thus conduct the representation-level semantic regularization. Extensive experiments on a public dataset have verified the superiority of our proposed MDS-S2. We have released the codes and parameters to facilitate the research community.

Beyond the Safeguards: Exploring the Security Risks of ChatGPT

The increasing popularity of large language models (LLMs) such as ChatGPT has led to growing concerns about their safety, security risks, and ethical implications. This paper aims to provide an overview of the different types of security risks associated with ChatGPT, including malicious text and code generation, private data disclosure, fraudulent services, information gathering, and producing unethical content. We present an empirical study examining the effectiveness of ChatGPT's content filters and explore potential ways to bypass these safeguards, demonstrating the ethical implications and security risks that persist in LLMs even when protections are in place. Based on a qualitative analysis of the security implications, we discuss potential strategies to mitigate these risks and inform researchers, policymakers, and industry professionals about the complex security challenges posed by LLMs like ChatGPT. This study contributes to the ongoing discussion on the ethical and security implications of LLMs, underscoring the need for continued research in this area.

Squeeze Excitation Embedded Attention UNet for Brain Tumor Segmentation

Deep Learning based techniques have gained significance over the past few years in the field of medicine. They are used in various applications such as classifying medical images, segmentation and identification. The existing architectures such as UNet, Attention UNet and Attention Residual UNet are already currently existing methods for the same application of brain tumor segmentation, but none of them address the issue of how to extract the features in channel level. In this paper, we propose a new architecture called Squeeze Excitation Embedded Attention UNet (SEEA-UNet), this architecture has both Attention UNet and Squeeze Excitation Network for better results and predictions, this is used mainly because to get information at both Spatial and channel levels. The proposed model was compared with the existing architectures based on the comparison it was found out that for lesser number of epochs trained, the proposed model performed better. Binary focal loss and Jaccard Coefficient were used to monitor the model's performance.

Gene Set Summarization using Large Language Models

Molecular biologists frequently interpret gene lists derived from high-throughput experiments and computational analysis. This is typically done as a statistical enrichment analysis that measures the over- or under-representation of biological function terms associated with genes or their properties, based on curated assertions from a knowledge base (KB) such as the Gene Ontology (GO). Interpreting gene lists can also be framed as a textual summarization task, enabling the use of Large Language Models (LLMs), potentially utilizing scientific texts directly and avoiding reliance on a KB. We developed SPINDOCTOR (Structured Prompt Interpolation of Natural Language Descriptions of Controlled Terms for Ontology Reporting), a method that uses GPT models to perform gene set function summarization as a complement to standard enrichment analysis. This method can use different sources of gene functional information: (1) structured text derived from curated ontological KB annotations, (2) ontology-free narrative gene summaries, or (3) direct model retrieval. We demonstrate that these methods are able to generate plausible and biologically valid summary GO term lists for gene sets. However, GPT-based approaches are unable to deliver reliable scores or p-values and often return terms that are not statistically significant. Crucially, these methods were rarely able to recapitulate the most precise and informative term from standard enrichment, likely due to an inability to generalize and reason using an ontology. Results are highly nondeterministic, with minor variations in prompt resulting in radically different term lists. Our results show that at this point, LLM-based methods are unsuitable as a replacement for standard term enrichment analysis and that manual curation of ontological assertions remains necessary.

Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One

Graph neural networks (GNN) suffer from severe inefficiency. It is mainly caused by the exponential growth of node dependency with the increase of layers. It extremely limits the application of stochastic optimization algorithms so that the training of GNN is usually time-consuming. To address this problem, we propose to decouple a multi-layer GNN as multiple simple modules for more efficient training, which is comprised of classical forward training (FT)and designed backward training (BT). Under the proposed framework, each module can be trained efficiently in FT by stochastic algorithms without distortion of graph information owing to its simplicity. To avoid the only unidirectional information delivery of FT and sufficiently train shallow modules with the deeper ones, we develop a backward training mechanism that makes the former modules perceive the latter modules. The backward training introduces the reversed information delivery into the decoupled modules as well as the forward information delivery. To investigate how the decoupling and greedy training affect the representational capacity, we theoretically prove that the error produced by linear modules will not accumulate on unsupervised tasks in most cases. The theoretical and experimental results show that the proposed framework is highly efficient with reasonable performance.

Emergent Cooperative Behavior in Distributed Target Tracking with Unknown Occlusions

Tracking multiple moving objects of interest (OOI) with multiple robot systems (MRS) has been addressed by active sensing that maintains a shared belief of OOIs and plans the motion of robots to maximize the information quality. Mobility of robots enables the behavior of pursuing better visibility, which is constrained by sensor field of view (FoV) and occlusion objects. We first extend prior work to detect, maintain and share occlusion information explicitly, allowing us to generate occlusion-aware planning even if a priori semantic occlusion information is unavailable. The efficacy of active sensing approaches is often evaluated according to estimation error and information gain metrics. However, these metrics do not directly explain the level of cooperative behavior engendered by the active sensing algorithms. Next, we extract different emergent cooperative behaviors that stem from the same underlying algorithms but manifest differently under differing scenarios. In particular, we highlight and demonstrate three emergent behavior patterns in active sensing MRS: (i) Change of tracking responsibility between agents when tracking trajectories with divergent directions or due to a re-allocation of the resource among heterogeneous agents; (ii) Awareness of occlusions to a trajectory and temporal leave-and-return of the sensing agent; (iii) Sharing of local occlusion objects in MRS that subsequently improves the awareness of occlusion.

Self-Attention in Colors: Another Take on Encoding Graph Structure in Transformers

We introduce a novel self-attention mechanism, which we call CSA (Chromatic Self-Attention), which extends the notion of attention scores to attention _filters_, independently modulating the feature channels. We showcase CSA in a fully-attentional graph Transformer CGT (Chromatic Graph Transformer) which integrates both graph structural information and edge features, completely bypassing the need for local message-passing components. Our method flexibly encodes graph structure through node-node interactions, by enriching the original edge features with a relative positional encoding scheme. We propose a new scheme based on random walks that encodes both structural and positional information, and show how to incorporate higher-order topological information, such as rings in molecular graphs. Our approach achieves state-of-the-art results on the ZINC benchmark dataset, while providing a flexible framework for encoding graph structure and incorporating higher-order topology.

Robust Hybrid Transceiver Designs for Linear Decentralized Estimation in mmWave MIMO IoT Networks in the Face of Imperfect CSI

Hybrid transceivers are designed for linear decentralized estimation (LDE) in a mmWave multiple-input multiple-output (MIMO) IoT network (IoTNe). For a noiseless fusion center (FC), it is demonstrated that the MSE performance is determined by the number of RF chains used at each IoT node (IoTNo). Next, the minimum-MSE RF transmit precoders (TPCs) and receive combiner (RC) matrices are designed for this setup using the dominant array response vectors, and subsequently, a closed-form expression is obtained for the baseband (BB) TPC at each IoTNo using Cauchy's interlacing theorem. For a realistic noisy FC, it is shown that the resultant mean squared error (MSE) minimization problem is non-convex. To address this challenge, a block-coordinate descent-based iterative scheme is proposed to obtain the fully digital TPC and RC matrices followed by the simultaneous orthogonal matching pursuit (SOMP) technique for decomposing the fully-digital transceiver into its corresponding RF and BB components. A theoretical proof of the convergence is also presented for the proposed iterative design procedure. Furthermore, robust hybrid transceiver designs are also derived for a practical scenario in the face of channel state information (CSI) uncertainty. The centralized MMSE lower bound has also been derived that benchmarks the performance of the proposed LDE schemes. Finally, our numerical results characterize the performance of the proposed transceivers as well as corroborate our various analytical propositions.

Taxonomy of AISecOps Threat Modeling for Cloud Based Medical Chatbots

Artificial Intelligence (AI) is playing a vital role in all aspects of technology including cyber security. Application of Conversational AI like the chatbots are also becoming very popular in the medical field to provide timely and immediate medical assistance to patients in need. As medical chatbots deal with a lot of sensitive information, the security of these chatbots is crucial. To secure the confidentiality, integrity, and availability of cloud-hosted assets like these, medical chatbots can be monitored using AISecOps (Artificial Intelligence for Secure IT Operations). AISecOPs is an emerging field that integrates three different but interrelated domains like the IT operation, AI, and security as one domain, where the expertise from all these three domains are used cohesively to secure the cyber assets. It considers cloud operations and security in a holistic framework to collect the metrics required to assess the security threats and train the AI models to take immediate actions. This work is focused on applying the STRIDE threat modeling framework to model the possible threats involved in each component of the chatbot to enable the automatic threat detection using the AISecOps techniques. This threat modeling framework is tailored to the medical chatbots that involves sensitive data sharing but could also be applied for chatbots used in other sectors like the financial services, public sector, and government sectors that are concerned with security and compliance.