Invariant molecular representation models provide potential solutions to guarantee accurate prediction of molecular properties under distribution shifts out-of-distribution (OOD) by identifying and leveraging invariant substructures inherent to the molecules. However, due to the complex entanglement of molecular functional groups and the frequent display of activity cliffs by molecular properties, the separation of molecules becomes inaccurate and tricky. This results in inconsistent semantics among the invariant substructures identified by existing models, which means molecules sharing identical invariant structures may exhibit drastically different properties. Focusing on the aforementioned challenges, in the semantic space, this paper explores the potential correlation between the consistent semantic-expressing the same information within different molecular representation forms-and the molecular property prediction problem. To enhance the performance of OOD molecular property prediction, this paper proposes a consistent semantic representation learning (CSRL) framework without separating molecules, which comprises two modules: a semantic uni-code (SUC) module and a consistent semantic extractor (CSE). To address inconsistent mapping of semantic in different molecular representation forms, SUC adjusts incorrect embeddings into the correct embeddings of two molecular representation forms. Then, CSE leverages non-semantic information as training labels to guide the discriminator's learning, thereby suppressing the reliance of CSE on the non-semantic information in different molecular representation embeddings. Extensive experiments demonstrate that the consistent semantic can guarantee the performance of models. Overall, CSRL can improve the model's average Receiver Operating Characteristic - Area Under the Curve (ROC-AUC) by 6.43%, when comparing with 11 state-of-the-art models on 12 datasets.

Received Signal Strength Indicator (RSSI)-based indoor localization offers a cost-effective solution for autonomous mobile robot navigation in 3D indoor environments, including cross-floor and multi-building structures. However, localization accuracy is fundamentally constrained by the low sampling density and unstable measurement of RSSI data. So far, existing methods neglect cross-environment RSSI coherence (e.g., repeated signal patterns in geometrically similar areas), resulting in unreliable fingerprint databases. What’s more, most approaches fail to model the spatial hierarchy of buildings, floors, and coordinates, which leads to lower accuracy in indoor positioning model predictions. To address these issues, we propose EP-3DLoc, a novel 3D indoor localization framework that combines an Environment-Invariant feature-based Data Completion (EIC) method with a Position-Related feature-based Localization (PRL) method. The EIC enhances data quality by filling in sparse RSSI data using environment-invariant features, which are recurring RSSI patterns found in similar environmental structures. The PRL module combines multi-scale RSSI signal processing (raw data and image-like data) with a multi-task network that analyzes location relationships, enhancing localization accuracy in 3D environments. Experimental results on public datasets (TUT2018, UTSIndoorLoc, and UJIIndoorLoc) have demonstrated that EP-3DLoc achieves state-of-the-art performance on indoor localization in multi-building environments. Further testing on the self-constructed dataset HZAUIndoorLoc have revealed that EP-3DLoc not only outperforms existing methods in localization accuracy but also maintains low energy consumption and strong resistance to interference. The dataset HZAUIndoorLoc is available at https://github.com/Hanzoe/HZAUIndoorLoc-Dataset.

Person re-identification (Re-ID) is a critical technology in security systems and video surveillance. However, most of the existing methods focused on precise Re-ID, which not only neglect the transmission overheads, computing energy consumption and carbon emissions, but are unsustainable. Furthermore, the personal semantics is usually blurred and distorted in real-world scenarios due to the bird's eye view (BEV) of cameras. Crossillumination and face-coverings also weakened the key personal semantics. Such deficiencies have resulted in a substantial amount of carbon emissions and poor Re-ID performance. To reduce the video transmission overheads, computing energy consumption and carbon emissions yet guaranteeing the accuracy of Re-ID, this paper proposes a novel semantic communication-based lowcarbon sustainable framework (SC-LCSF) for Re-ID. SC-LCSF adopts the semantic encoder based on an enhanced semanticsaware attention mechanism (ESA-SE) to extract the personal semantics. Only semantic information is transmitted at the semantic layer, which is then decoded into personal IDs by the multi-granularity semantic decoder (MG-SD). Two widely used public datasets, Market-1501 and CUHK03, and a newly curated real-world dataset, HZAU-SCUEC01, are used to train SC-LCSF and to evaluate its performance. Experimental results show that compared to the state-of-the-art (SOTA) methods, SC-LCSF achieves the best Rank-1 and mAP accuracy on all the datasets. Furthermore, SC-LCSF has a significant performance enhancement in low-carbon sustainable computing – the transmission data amount, CPU power consumption, CPU temperature, GPU power consumption, GPU temperature and Re-ID delay have a reduction of 96.8%, 39.6%, 27.9%, 40.9%, 29.7% and 76.6%, respectively.

Molecular representation learning is widely used in the field of drug discovery, due to its ability to accurately capture the complex features of compounds in high-dimensional space. However, existing molecular representation learning models are prone to be influenced by spurious parts during distribution shifts (also known as out-of-distribution, or OOD), which results in models mistakenly treating these spurious parts as crucial features of molecules, thereby limiting the generalization capability of the models. To tackle this issue, a novel invariant molecular representation learning model, called Causal Invariant Hierarchical Molecular Representation Graph Neural Networks (CHiMoGNN), is proposed for OOD molecular property prediction. In CHiMoGNN, a Feature Enhancement (FE) module is designed to leverage the multi-level molecular parts to enhance the expression of invariant features, thereby enhancing the model’s capability to capture key molecular information. In addition, a Cartesian Product based Environmental Impact (EI) module is adopted to generate counterfactual samples with environmental diversity. Consequently, these samples are utilized to train a classifier that maintains consistent performance across various environments. Extensive experiments on seven real-world datasets demonstrate that CHiMoGNN outperforms 9 state-of-the-art models, achieving a 5.73% increase in average ROC-AUC, and the results also show that CHiMoGNN can effectively maintain generalization in various distribution shifts. Code and datasets are available at https://github.com/Chertuion/CHiMoGNN.

Obtaining accurate and effective information for drug molecules is a crucial and challenging task, which relies on high-quality chemical knowledge. However, chemical knowledge has been accumulated over the past 100 years from various regions, laboratories, and experimental purposes, which contains a lot of noise and inconsistency, leading to the out-of-distribution (OOD) problem. OOD may results in weak robustness and unsatisfied performance. In order to solve OOD learning problem with noise, a novel benchmark: ADMEOOD is proposed, which is a systematic OOD dataset curator and specifically designed for drug property prediction. ADMEOOD screens 27 Absorption, Distribution, Metabolism and Excretion (ADME) drug properties from Chembl and relevant literature. This paper explicitly make distinctions between two kinds of OOD data shifts: Noise Shift and Concept Conflict Drift (CCD). Overall, ADME contains 6 domain annotations combined with noise, CCD and no shifts, resulting in 18 different splits in total. ADMEOOD provides performance results on a variety of SOTA OOD models. The results demonstrate a significant difference performance between in-distribution and OOD data. Moreover, Empirical Risk Minimization and other models exhibit distinct trends in different domains and measurement types. The ADMEOOD benchmark can be accessed via https://github.com/qweasdzxc-wsy/ADMEOOD/.

Indoor localization technology based on the Received Signal Strength Indicator (RSSI) holds significant practical promise for mobile robots. However, accuracy is directly diminished due to the challenge of precisely establishing correlations among 3D positional data (buildings, floors, and coordinates) from RSSI, as well as RSSI fluctuations caused by numerous signal interferences. This demonstration proposes MMLoc, a 3D indoor localization system for mobile robots. To enhance positional features, MMLoc reshapes one-dimensional RSSI data into images and jointly utilizes them as inputs to a prediction model. To further optimize the model's performance, the building prediction task works as a prerequisite for floor and coordinate prediction tasks, followed by staged feature extraction and multidimensional data fusion. Experimental results on a JetBot demonstrate that MMLoc has achieved high-precision 3D indoor localization.