We propose a multimodal spatiotemporal graph neural network (STG) framework to predict colorectal cancer liver metastasis (CRLM) progression. Current clinical models do not effectively integrate the tumor's spatial heterogeneity, dynamic evolution, and complex multimodal data relationships, limiting their predictive accuracy. Our STG framework combines preoperative CT imaging and clinical data into a heterogeneous graph structure, enabling joint modeling of tumor distribution and temporal evolution through spatial topology and cross-modal edges. The framework uses GraphSAGE to aggregate spatiotemporal neighborhood information and leverages supervised and contrastive learning strategies to enhance the model's ability to capture temporal features and improve robustness. A lightweight version of the model reduces parameter count by 78.55%, maintaining near-state-of-the-art performance. The model jointly optimizes recurrence risk regression and survival analysis tasks, with contrastive loss improving feature representational discriminability and cross-modal consistency. Experimental results on the MSKCC CRLM dataset show a time-adjacent accuracy of 85% and a mean absolute error of 1.1005, significantly outperforming existing methods. The innovative heterogeneous graph construction and spatiotemporal decoupling mechanism effectively uncover the associations between dynamic tumor microenvironment changes and prognosis, providing reliable quantitative support for personalized treatment decisions.
Accurate MRI-to-CT translation promises the integration of complementary imaging information without the need for additional imaging sessions. Given the practical challenges associated with acquiring paired MRI and CT scans, the development of robust methods capable of leveraging unpaired datasets is essential for advancing the MRI-to-CT translation. Current unpaired MRI-to-CT translation methods, which predominantly rely on cycle consistency and contrastive learning frameworks, frequently encounter challenges in accurately translating anatomical features that are highly discernible on CT but less distinguishable on MRI, such as bone structures. This limitation renders these approaches less suitable for applications in radiation therapy, where precise bone representation is essential for accurate treatment planning. To address this challenge, we propose a path- and bone-contour regularized approach for unpaired MRI-to-CT translation. In our method, MRI and CT images are projected to a shared latent space, where the MRI-to-CT mapping is modeled as a continuous flow governed by neural ordinary differential equations. The optimal mapping is obtained by minimizing the transition path length of the flow. To enhance the accuracy of translated bone structures, we introduce a trainable neural network to generate bone contours from MRI and implement mechanisms to directly and indirectly encourage the model to focus on bone contours and their adjacent regions. Evaluations conducted on three datasets demonstrate that our method outperforms existing unpaired MRI-to-CT translation approaches, achieving lower overall error rates. Moreover, in a downstream bone segmentation task, our approach exhibits superior performance in preserving the fidelity of bone structures. Our code is available at: https://github.com/kennysyp/PaBoT.
Unsupervised visible-infrared person re-identification (USL-VI-ReID) seeks to match pedestrian images of the same individual across different modalities without human annotations for model learning. Previous methods unify pseudo-labels of cross-modality images through label association algorithms and then design contrastive learning framework for global feature learning. However, these methods overlook the cross-modality variations in feature representation and pseudo-label distributions brought by fine-grained patterns. This insight results in insufficient modality-shared learning when only global features are optimized. To address this issue, we propose a Semantic-Aligned Learning with Collaborative Refinement (SALCR) framework, which builds up optimization objective for specific fine-grained patterns emphasized by each modality, thereby achieving complementary alignment between the label distributions of different modalities. Specifically, we first introduce a Dual Association with Global Learning (DAGI) module to unify the pseudo-labels of cross-modality instances in a bi-directional manner. Afterward, a Fine-Grained Semantic-Aligned Learning (FGSAL) module is carried out to explore part-level semantic-aligned patterns emphasized by each modality from cross-modality instances. Optimization objective is then formulated based on the semantic-aligned features and their corresponding label space. To alleviate the side-effects arising from noisy pseudo-labels, we propose a Global-Part Collaborative Refinement (GPCR) module to mine reliable positive sample sets for the global and part features dynamically and optimize the inter-instance relationships. Extensive experiments demonstrate the effectiveness of the proposed method, which achieves superior performances to state-of-the-art methods. Our code is available at \href{https://github.com/FranklinLingfeng/code-for-SALCR}.
The rapid advancements in Large Vision Language Models (LVLMs) offer the potential to surpass conventional labeling by generating richer, more detailed descriptions of on-device human behavior understanding (HBU) in low-resolution vision systems, such as depth, thermal, and infrared. However, existing large vision language model (LVLM) approaches are unable to understand low-resolution data well as they are primarily designed for high-resolution data, such as RGB images. A quick fixing approach is to caption a large amount of low-resolution data, but it requires a significant amount of labor-intensive annotation efforts. In this paper, we propose a novel, labor-saving system, Llambda, designed to support low-resolution HBU. The core idea is to leverage limited labeled data and a large amount of unlabeled data to guide LLMs in generating informative captions, which can be combined with raw data to effectively fine-tune LVLM models for understanding low-resolution videos in HBU. First, we propose a Contrastive-Oriented Data Labeler, which can capture behavior-relevant information from long, low-resolution videos and generate high-quality pseudo labels for unlabeled data via contrastive learning. Second, we propose a Physical-Knowledge Guided Captioner, which utilizes spatial and temporal consistency checks to mitigate errors in pseudo labels. Therefore, it can improve LLMs' understanding of sequential data and then generate high-quality video captions. Finally, to ensure on-device deployability, we employ LoRA-based efficient fine-tuning to adapt LVLMs for low-resolution data. We evaluate Llambda using a region-scale real-world testbed and three distinct low-resolution datasets, and the experiments show that Llambda outperforms several state-of-the-art LVLM systems up to $40.03\%$ on average Bert-Score.
Unsupervised contrastive learning has become a hot research topic in natural language processing. Existing works usually aim at constraining the orientation distribution of the representations of positive and negative samples in the high-dimensional semantic space in contrastive learning, but the semantic representation tensor possesses both modulus and orientation features, and the existing works ignore the modulus feature of the representations and cause insufficient contrastive learning. % Therefore, we firstly propose a training objective that aims at modulus constraints on the semantic representation tensor, to strengthen the alignment between the positive samples in contrastive learning. Therefore, we first propose a training objective that is designed to impose modulus constraints on the semantic representation tensor, to strengthen the alignment between positive samples in contrastive learning. Then, the BERT-like model suffers from the phenomenon of sinking attention, leading to a lack of attention to CLS tokens that aggregate semantic information. In response, we propose a cross-attention structure among the twin-tower ensemble models to enhance the model's attention to CLS token and optimize the quality of CLS Pooling. Combining the above two motivations, we propose a new \textbf{J}oint \textbf{T}ensor representation modulus constraint and \textbf{C}ross-attention unsupervised contrastive learning \textbf{S}entence \textbf{E}mbedding representation framework JTCSE, which we evaluate in seven semantic text similarity computation tasks, and the experimental results show that JTCSE's twin-tower ensemble model and single-tower distillation model outperform the other baselines and become the current SOTA. In addition, we have conducted an extensive zero-shot downstream task evaluation, which shows that JTCSE outperforms other baselines overall on more than 130 tasks.
Audiovisual emotion recognition (AVER) aims to infer human emotions from nonverbal visual-audio (VA) cues, offering modality-complementary and language-agnostic advantages. However, AVER remains challenging due to the inherent ambiguity of emotional expressions, cross-modal expressive disparities, and the scarcity of reliably annotated data. Recent self-supervised AVER approaches have introduced strong multimodal representations, yet they predominantly rely on modality-specific encoders and coarse content-level alignment, limiting fine-grained emotional semantic modeling. To address these issues, we propose VAEmo, an efficient two-stage framework for emotion-centric joint VA representation learning with external knowledge injection. In Stage 1, a unified and lightweight representation network is pre-trained on large-scale speaker-centric VA corpora via masked reconstruction and contrastive objectives, mitigating the modality gap and learning expressive, complementary representations without emotion labels. In Stage 2, multimodal large language models automatically generate detailed affective descriptions according to our well-designed chain-of-thought prompting for only a small subset of VA samples; these rich textual semantics are then injected by aligning their corresponding embeddings with VA representations through dual-path contrastive learning, further bridging the emotion gap. Extensive experiments on multiple downstream AVER benchmarks show that VAEmo achieves state-of-the-art performance with a compact design, highlighting the benefit of unified cross-modal encoding and emotion-aware semantic guidance for efficient, generalizable VA emotion representations.
Weakly-supervised video anomaly detection (WS-VAD) using Multiple Instance Learning (MIL) suffers from label ambiguity, hindering discriminative feature learning. We propose ProDisc-VAD, an efficient framework tackling this via two synergistic components. The Prototype Interaction Layer (PIL) provides controlled normality modeling using a small set of learnable prototypes, establishing a robust baseline without being overwhelmed by dominant normal data. The Pseudo-Instance Discriminative Enhancement (PIDE) loss boosts separability by applying targeted contrastive learning exclusively to the most reliable extreme-scoring instances (highest/lowest scores). ProDisc-VAD achieves strong AUCs (97.98% ShanghaiTech, 87.12% UCF-Crime) using only 0.4M parameters, over 800x fewer than recent ViT-based methods like VadCLIP, demonstrating exceptional efficiency alongside state-of-the-art performance. Code is available at https://github.com/modadundun/ProDisc-VAD.
Electroencephalography (EEG) signals provide a promising and involuntary reflection of brain activity related to emotional states, offering significant advantages over behavioral cues like facial expressions. However, EEG signals are often noisy, affected by artifacts, and vary across individuals, complicating emotion recognition. While multimodal approaches have used Peripheral Physiological Signals (PPS) like GSR to complement EEG, they often overlook the dynamic synchronization and consistent semantics between the modalities. Additionally, the temporal dynamics of emotional fluctuations across different time resolutions in PPS remain underexplored. To address these challenges, we propose PhysioSync, a novel pre-training framework leveraging temporal and cross-modal contrastive learning, inspired by physiological synchronization phenomena. PhysioSync incorporates Cross-Modal Consistency Alignment (CM-CA) to model dynamic relationships between EEG and complementary PPS, enabling emotion-related synchronizations across modalities. Besides, it introduces Long- and Short-Term Temporal Contrastive Learning (LS-TCL) to capture emotional synchronization at different temporal resolutions within modalities. After pre-training, cross-resolution and cross-modal features are hierarchically fused and fine-tuned to enhance emotion recognition. Experiments on DEAP and DREAMER datasets demonstrate PhysioSync's advanced performance under uni-modal and cross-modal conditions, highlighting its effectiveness for EEG-centered emotion recognition.
We propose a generalization of modern representation learning objectives by reframing them as recursive divergence alignment processes over localized conditional distributions While recent frameworks like Information Contrastive Learning I-Con unify multiple learning paradigms through KL divergence between fixed neighborhood conditionals we argue this view underplays a crucial recursive structure inherent in the learning process. We introduce Recursive KL Divergence Optimization RKDO a dynamic formalism where representation learning is framed as the evolution of KL divergences across data neighborhoods. This formulation captures contrastive clustering and dimensionality reduction methods as static slices while offering a new path to model stability and local adaptation. Our experiments demonstrate that RKDO offers dual efficiency advantages approximately 30 percent lower loss values compared to static approaches across three different datasets and 60 to 80 percent reduction in computational resources needed to achieve comparable results. This suggests that RKDOs recursive updating mechanism provides a fundamentally more efficient optimization landscape for representation learning with significant implications for resource constrained applications.
Contrastive learning has proven effective in training sequential recommendation models by incorporating self-supervised signals from augmented views. Most existing methods generate multiple views from the same interaction sequence through stochastic data augmentation, aiming to align their representations in the embedding space. However, users typically have specific intents when purchasing items (e.g., buying clothes as gifts or cosmetics for beauty). Random data augmentation used in existing methods may introduce noise, disrupting the latent intent information implicit in the original interaction sequence. Moreover, using noisy augmented sequences in contrastive learning may mislead the model to focus on irrelevant features, distorting the embedding space and failing to capture users' true behavior patterns and intents. To address these issues, we propose Intent-aware Diffusion with contrastive learning for sequential Recommendation (InDiRec). The core idea is to generate item sequences aligned with users' purchasing intents, thus providing more reliable augmented views for contrastive learning. Specifically, InDiRec first performs intent clustering on sequence representations using K-means to build intent-guided signals. Next, it retrieves the intent representation of the target interaction sequence to guide a conditional diffusion model, generating positive views that share the same underlying intent. Finally, contrastive learning is applied to maximize representation consistency between these intent-aligned views and the original sequence. Extensive experiments on five public datasets demonstrate that InDiRec achieves superior performance compared to existing baselines, learning more robust representations even under noisy and sparse data conditions.
Modeling holistic user interests is important for improving recommendation systems but is challenged by high computational cost and difficulty in handling diverse information with full behavior context. Existing search-based methods might lose critical signals during behavior selection. To overcome these limitations, we propose CHIME: A Compressive Framework for Holistic Interest Modeling. It uses adapted large language models to encode complete user behaviors with heterogeneous inputs. We introduce multi-granular contrastive learning objectives to capture both persistent and transient interest patterns and apply residual vector quantization to generate compact embeddings. CHIME demonstrates superior ranking performance across diverse datasets, establishing a robust solution for scalable holistic interest modeling in recommendation systems.
Interpreting neural activity through meaningful latent representations remains a complex and evolving challenge at the intersection of neuroscience and artificial intelligence. We investigate the potential of multimodal foundation models to align invasive brain recordings with natural language. We present SSENSE, a contrastive learning framework that projects single-subject stereo-electroencephalography (sEEG) signals into the sentence embedding space of a frozen CLIP model, enabling sentence-level retrieval directly from brain activity. SSENSE trains a neural encoder on spectral representations of sEEG using InfoNCE loss, without fine-tuning the text encoder. We evaluate our method on time-aligned sEEG and spoken transcripts from a naturalistic movie-watching dataset. Despite limited data, SSENSE achieves promising results, demonstrating that general-purpose language representations can serve as effective priors for neural decoding.
Advancements in audio neural networks have established state-of-the-art results on downstream audio tasks. However, the black-box structure of these models makes it difficult to interpret the information encoded in their internal audio representations. In this work, we explore the semantic interpretability of audio embeddings extracted from these neural networks by leveraging CLAP, a contrastive learning model that brings audio and text into a shared embedding space. We implement a post-hoc method to transform CLAP embeddings into concept-based, sparse representations with semantic interpretability. Qualitative and quantitative evaluations show that the concept-based representations outperform or match the performance of original audio embeddings on downstream tasks while providing interpretability. Additionally, we demonstrate that fine-tuning the concept-based representations can further improve their performance on downstream tasks. Lastly, we publish three audio-specific vocabularies for concept-based interpretability of audio embeddings.
The training of artificial neural networks is heavily dependent on the careful selection of an appropriate loss function. While commonly used loss functions, such as cross-entropy and mean squared error (MSE), generally suffice for a broad range of tasks, challenges often emerge due to limitations in data quality or inefficiencies within the learning process. In such circumstances, the integration of supplementary terms into the loss function can serve to address these challenges, enhancing both model performance and robustness. Two prominent techniques, loss regularization and contrastive learning, have been identified as effective strategies for augmenting the capacity of loss functions in artificial neural networks. Knowledge tracing is a compelling area of research that leverages predictive artificial intelligence to facilitate the automation of personalized and efficient educational experiences for students. In this paper, we provide a comprehensive review of the deep learning-based knowledge tracing (DKT) algorithms trained using advanced loss functions and discuss their improvements over prior techniques. We discuss contrastive knowledge tracing algorithms, such as Bi-CLKT, CL4KT, SP-CLKT, CoSKT, and prediction-consistent DKT, providing performance benchmarks and insights into real-world deployment challenges. The survey concludes with future research directions, including hybrid loss strategies and context-aware modeling.
Ensuring the safety of generated content remains a fundamental challenge for Text-to-Image (T2I) generation. Existing studies either fail to guarantee complete safety under potentially harmful concepts or struggle to balance safety with generation quality. To address these issues, we propose Safety-Constrained Direct Preference Optimization (SC-DPO), a novel framework for safety alignment in T2I models. SC-DPO integrates safety constraints into the general human preference calibration, aiming to maximize the likelihood of generating human-preferred samples while minimizing the safety cost of the generated outputs. In SC-DPO, we introduce a safety cost model to accurately quantify harmful levels for images, and train it effectively using the proposed contrastive learning and cost anchoring objectives. To apply SC-DPO for effective T2I safety alignment, we constructed SCP-10K, a safety-constrained preference dataset containing rich harmful concepts, which blends safety-constrained preference pairs under both harmful and clean instructions, further mitigating the trade-off between safety and sample quality. Additionally, we propose a Dynamic Focusing Mechanism (DFM) for SC-DPO, promoting the model's learning of difficult preference pair samples. Extensive experiments demonstrate that SC-DPO outperforms existing methods, effectively defending against various NSFW content while maintaining optimal sample quality and human preference alignment. Additionally, SC-DPO exhibits resilience against adversarial prompts designed to generate harmful content.
Sound source localization (SSL) is the task of locating the source of sound within an image. Due to the lack of localization labels, the de facto standard in SSL has been to represent an image and audio as a single embedding vector each, and use them to learn SSL via contrastive learning. To this end, previous work samples one of local image features as the image embedding and aggregates all local audio features to obtain the audio embedding, which is far from optimal due to the presence of noise and background irrelevant to the actual target in the input. We present a novel SSL method that addresses this chronic issue by joint slot attention on image and audio. To be specific, two slots competitively attend image and audio features to decompose them into target and off-target representations, and only target representations of image and audio are used for contrastive learning. Also, we introduce cross-modal attention matching to further align local features of image and audio. Our method achieved the best in almost all settings on three public benchmarks for SSL, and substantially outperformed all the prior work in cross-modal retrieval.
Time series anomaly detection holds notable importance for risk identification and fault detection across diverse application domains. Unsupervised learning methods have become popular because they have no requirement for labels. However, due to the challenges posed by the multiplicity of abnormal patterns, the sparsity of anomalies, and the growth of data scale and complexity, these methods often fail to capture robust and representative dependencies within the time series for identifying anomalies. To enhance the ability of models to capture normal patterns of time series and avoid the retrogression of modeling ability triggered by the dependencies on high-quality prior knowledge, we propose a differencing-based contrastive representation learning framework for time series anomaly detection (DConAD). Specifically, DConAD generates differential data to provide additional information about time series and utilizes transformer-based architecture to capture spatiotemporal dependencies, which enhances the robustness of unbiased representation learning ability. Furthermore, DConAD implements a novel KL divergence-based contrastive learning paradigm that only uses positive samples to avoid deviation from reconstruction and deploys the stop-gradient strategy to compel convergence. Extensive experiments on five public datasets show the superiority and effectiveness of DConAD compared with nine baselines. The code is available at https://github.com/shaieesss/DConAD.
Reinforcement learning (RL) has made significant progress in various domains, but scaling it to long-horizon tasks with complex decision-making remains challenging. Skill learning attempts to address this by abstracting actions into higher-level behaviors. However, current approaches often fail to recognize semantically similar behaviors as the same skill and use fixed skill lengths, limiting flexibility and generalization. To address this, we propose Dynamic Contrastive Skill Learning (DCSL), a novel framework that redefines skill representation and learning. DCSL introduces three key ideas: state-transition based skill representation, skill similarity function learning, and dynamic skill length adjustment. By focusing on state transitions and leveraging contrastive learning, DCSL effectively captures the semantic context of behaviors and adapts skill lengths to match the appropriate temporal extent of behaviors. Our approach enables more flexible and adaptive skill extraction, particularly in complex or noisy datasets, and demonstrates competitive performance compared to existing methods in task completion and efficiency.
Medical image segmentation is a critical yet challenging task, primarily due to the difficulty of obtaining extensive datasets of high-quality, expert-annotated images. Contrastive learning presents a potential but still problematic solution to this issue. Because most existing methods focus on extracting instance-level or pixel-to-pixel representation, which ignores the characteristics between intra-image similar pixel groups. Moreover, when considering contrastive pairs generation, most SOTA methods mainly rely on manually setting thresholds, which requires a large number of gradient experiments and lacks efficiency and generalization. To address these issues, we propose a novel contrastive learning approach named SuperCL for medical image segmentation pre-training. Specifically, our SuperCL exploits the structural prior and pixel correlation of images by introducing two novel contrastive pairs generation strategies: Intra-image Local Contrastive Pairs (ILCP) Generation and Inter-image Global Contrastive Pairs (IGCP) Generation. Considering superpixel cluster aligns well with the concept of contrastive pairs generation, we utilize the superpixel map to generate pseudo masks for both ILCP and IGCP to guide supervised contrastive learning. Moreover, we also propose two modules named Average SuperPixel Feature Map Generation (ASP) and Connected Components Label Generation (CCL) to better exploit the prior structural information for IGCP. Finally, experiments on 8 medical image datasets indicate our SuperCL outperforms existing 12 methods. i.e. Our SuperCL achieves a superior performance with more precise predictions from visualization figures and 3.15%, 5.44%, 7.89% DSC higher than the previous best results on MMWHS, CHAOS, Spleen with 10% annotations. Our code will be released after acceptance.
Sequential recommendation is an extensively explored approach to capturing users' evolving preferences based on past interactions, aimed at predicting their next likely choice. Despite significant advancements in this domain, including methods based on RNNs and self-attention, challenges like limited supervised signals and noisy data caused by unintentional clicks persist. To address these challenges, some studies have incorporated unsupervised learning by leveraging local item contexts within individual sequences. However, these methods often overlook the intricate associations between items across multiple sequences and are susceptible to noise in item co-occurrence patterns. In this context, we introduce a novel framework, Global Unsupervised Data-Augmentation (UDA4SR), which adopts a graph contrastive learning perspective to generate more robust item embeddings for sequential recommendation. Our approach begins by integrating Generative Adversarial Networks (GANs) for data augmentation, which serves as the first step to enhance the diversity and richness of the training data. Then, we build a Global Item Relationship Graph (GIG) based on all user interaction sequences. Subsequently, we employ graph contrastive learning on the refined graph to enhance item embeddings by capturing complex global associations. To model users' dynamic and diverse interests more effectively, we enhance the CapsNet module with a novel target-attention mechanism. Extensive experiments show that UDA4SR significantly outperforms state-of-the-art approaches.