Human motion generation is a cut-edge area of research in generative computer vision, with promising applications in video creation, game development, and robotic manipulation. The recent Mamba architecture shows promising results in efficiently modeling long and complex sequences, yet two significant challenges remain: Firstly, directly applying Mamba to extended motion generation is ineffective, as the limited capacity of the implicit memory leads to memory decay. Secondly, Mamba struggles with multimodal fusion compared to Transformers, and lack alignment with textual queries, often confusing directions (left or right) or omitting parts of longer text queries. To address these challenges, our paper presents three key contributions: Firstly, we introduce KMM, a novel architecture featuring Key frame Masking Modeling, designed to enhance Mamba's focus on key actions in motion segments. This approach addresses the memory decay problem and represents a pioneering method in customizing strategic frame-level masking in SSMs. Additionally, we designed a contrastive learning paradigm for addressing the multimodal fusion problem in Mamba and improving the motion-text alignment. Finally, we conducted extensive experiments on the go-to dataset, BABEL, achieving state-of-the-art performance with a reduction of more than 57% in FID and 70% parameters compared to previous state-of-the-art methods. See project website: https://steve-zeyu-zhang.github.io/KMM
In the past two years, large language models (LLMs) have achieved rapid development and demonstrated remarkable emerging capabilities. Concurrently, with powerful semantic understanding and reasoning capabilities, LLMs have significantly empowered the rapid advancement of the recommendation system field. Specifically, in news recommendation (NR), systems must comprehend and process a vast amount of clicked news text to infer the probability of candidate news clicks. This requirement exceeds the capabilities of traditional NR models but aligns well with the strengths of LLMs. In this paper, we propose a novel NR algorithm to reshape the news model via LLM Embedding and Co-Occurrence Pattern (LECOP). On one hand, we fintuned LLM by contrastive learning using large-scale datasets to encode news, which can fully explore the semantic information of news to thoroughly identify user preferences. On the other hand, we explored multiple co-occurrence patterns to mine collaborative information. Those patterns include news ID co-occurrence, Item-Item keywords co-occurrence and Intra-Item keywords co-occurrence. The keywords mentioned above are all generated by LLM. As far as we know, this is the first time that constructing such detailed Co-Occurrence Patterns via LLM to capture collaboration. Extensive experiments demonstrate the superior performance of our proposed novel method
Commonsense question answering is a crucial task that requires machines to employ reasoning according to commonsense. Previous studies predominantly employ an extracting-and-modeling paradigm to harness the information in KG, which first extracts relevant subgraphs based on pre-defined rules and then proceeds to design various strategies aiming to improve the representations and fusion of the extracted structural knowledge. Despite their effectiveness, there are still two challenges. On one hand, subgraphs extracted by rule-based methods may have the potential to overlook critical nodes and result in uncontrollable subgraph size. On the other hand, the misalignment between graph and text modalities undermines the effectiveness of knowledge fusion, ultimately impacting the task performance. To deal with the problems above, we propose a novel framework: \textbf{S}ubgraph R\textbf{E}trieval Enhanced by Gra\textbf{P}h-\textbf{T}ext \textbf{A}lignment, named \textbf{SEPTA}. Firstly, we transform the knowledge graph into a database of subgraph vectors and propose a BFS-style subgraph sampling strategy to avoid information loss, leveraging the analogy between BFS and the message-passing mechanism. In addition, we propose a bidirectional contrastive learning approach for graph-text alignment, which effectively enhances both subgraph retrieval and knowledge fusion. Finally, all the retrieved information is combined for reasoning in the prediction module. Extensive experiments on five datasets demonstrate the effectiveness and robustness of our framework.
Contrastive learning has been a leading paradigm for self-supervised learning, but it is widely observed that it comes at the price of sacrificing useful features (\eg colors) by being invariant to data augmentations. Given this limitation, there has been a surge of interest in equivariant self-supervised learning (E-SSL) that learns features to be augmentation-aware. However, even for the simplest rotation prediction method, there is a lack of rigorous understanding of why, when, and how E-SSL learns useful features for downstream tasks. To bridge this gap between practice and theory, we establish an information-theoretic perspective to understand the generalization ability of E-SSL. In particular, we identify a critical explaining-away effect in E-SSL that creates a synergy between the equivariant and classification tasks. This synergy effect encourages models to extract class-relevant features to improve its equivariant prediction, which, in turn, benefits downstream tasks requiring semantic features. Based on this perspective, we theoretically analyze the influence of data transformations and reveal several principles for practical designs of E-SSL. Our theory not only aligns well with existing E-SSL methods but also sheds light on new directions by exploring the benefits of model equivariance. We believe that a theoretically grounded understanding on the role of equivariance would inspire more principled and advanced designs in this field. Code is available at https://github.com/kaotty/Understanding-ESSL.
Graph representation learning (GRL) is a fundamental task in machine learning, aiming to encode high-dimensional graph-structured data into low-dimensional vectors. Self-supervised learning (SSL) methods are widely used in GRL because they can avoid expensive human annotation. In this work, we propose a novel Subgraph Gaussian Embedding Contrast (SGEC) method. Our approach introduces a subgraph Gaussian embedding module, which adaptively maps subgraphs to a structured Gaussian space, ensuring the preservation of graph characteristics while controlling the distribution of generated subgraphs. We employ optimal transport distances, including Wasserstein and Gromov-Wasserstein distances, to effectively measure the similarity between subgraphs, enhancing the robustness of the contrastive learning process. Extensive experiments across multiple benchmarks demonstrate that SGEC outperforms or presents competitive performance against state-of-the-art approaches. Our findings provide insights into the design of SSL methods for GRL, emphasizing the importance of the distribution of the generated contrastive pairs.
Zero-shot anomaly detection (ZSAD) is crucial for detecting anomalous patterns in target datasets without using training samples, specifically in scenarios where there are distributional differences between the target domain and training data or where data scarcity arises because of restricted access. Although recently pretrained vision-language models demonstrate strong zero-shot performance across various visual tasks, they focus on learning class semantics, which makes their direct application to ZSAD challenging. To address this scenario, we propose GlocalCLIP, which uniquely separates global and local prompts and jointly optimizes them. This approach enables the object-agnostic glocal semantic prompt to effectively capture general normal and anomalous patterns without dependency on specific objects in the image. We refine the text prompts for more precise adjustments by utilizing deep-text prompt tuning in the text encoder. In the vision encoder, we apply V-V attention layers to capture detailed local image features. Finally, we introduce glocal contrastive learning to improve the complementary learning of global and local prompts, effectively detecting anomalous patterns across various domains. The generalization performance of GlocalCLIP in ZSAD was demonstrated on 15 real-world datasets from both the industrial and medical domains, achieving superior performance compared to existing methods. Code will be made available at https://github.com/YUL-git/GlocalCLIP.
Handling implicit language is essential for natural language processing systems to achieve precise text understanding and facilitate natural interactions with users. Despite its importance, the absence of a metric for accurately measuring the implicitness of language significantly constrains the depth of analysis possible in evaluating models' comprehension capabilities. This paper addresses this gap by developing a scalar metric that quantifies the implicitness level of language without relying on external references. Drawing on principles from traditional linguistics, we define ''implicitness'' as the divergence between semantic meaning and pragmatic interpretation. To operationalize this definition, we introduce ImpScore, a novel, reference-free metric formulated through an interpretable regression model. This model is trained using pairwise contrastive learning on a specially curated dataset comprising $112,580$ (implicit sentence, explicit sentence) pairs. We validate ImpScore through a user study that compares its assessments with human evaluations on out-of-distribution data, demonstrating its accuracy and strong correlation with human judgments. Additionally, we apply ImpScore to hate speech detection datasets, illustrating its utility and highlighting significant limitations in current large language models' ability to understand highly implicit content.
Early identification of stroke is crucial for intervention, requiring reliable models. We proposed an efficient retinal image representation together with clinical information to capture a comprehensive overview of cardiovascular health, leveraging large multimodal datasets for new medical insights. Our approach is one of the first contrastive frameworks that integrates graph and tabular data, using vessel graphs derived from retinal images for efficient representation. This method, combined with multimodal contrastive learning, significantly enhances stroke prediction accuracy by integrating data from multiple sources and using contrastive learning for transfer learning. The self-supervised learning techniques employed allow the model to learn effectively from unlabeled data, reducing the dependency on large annotated datasets. Our framework showed an AUROC improvement of 3.78% from supervised to self-supervised approaches. Additionally, the graph-level representation approach achieved superior performance to image encoders while significantly reducing pre-training and fine-tuning runtimes. These findings indicate that retinal images are a cost-effective method for improving cardiovascular disease predictions and pave the way for future research into retinal and cerebral vessel connections and the use of graph-based retinal vessel representations.
The attention to table understanding using recent natural language models has been growing. However, most related works tend to focus on learning the structure of the table directly. Just as humans improve their understanding of sentences by comparing them, they can also enhance their understanding by comparing tables. With this idea, in this paper, we introduce ACCIO, tAble understanding enhanCed via Contrastive learnIng with aggregatiOns, a novel approach to enhancing table understanding by contrasting original tables with their pivot summaries through contrastive learning. ACCIO trains an encoder to bring these table pairs closer together. Through validation via column type annotation, ACCIO achieves competitive performance with a macro F1 score of 91.1 compared to state-of-the-art methods. This work represents the first attempt to utilize pairs of tables for table embedding, promising significant advancements in table comprehension. Our code is available at https://github.com/whnhch/ACCIO/.
CLIP is a foundational multimodal model that aligns image and text features into a shared representation space via contrastive learning on large-scale image-text pairs. Its effectiveness primarily stems from the use of natural language as rich supervision. Motivated by the remarkable advancements in large language models (LLMs), this work explores how LLMs' superior text understanding and extensive open-world knowledge can enhance CLIP's capability, especially for processing longer and more complex image captions. We propose an efficient post-training strategy that integrates LLMs into pretrained CLIP. To address the challenge posed by the autoregressive nature of LLMs, we introduce a caption-to-caption contrastive fine-tuning framework, significantly enhancing the discriminative quality of LLM outputs. Extensive experiments demonstrate that our approach outperforms LoRA-based methods, achieving nearly fourfold faster training with superior performance. Furthermore, we validate substantial improvements over state-of-the-art models such as CLIP, EVA02, and SigLip2 across various zero-shot multimodal retrieval tasks, cross-lingual retrieval tasks, and multimodal language model pretraining.
Understanding the intricate cellular environment within biological tissues is crucial for uncovering insights into complex biological functions. While single-cell RNA sequencing has significantly enhanced our understanding of cellular states, it lacks the spatial context necessary to fully comprehend the cellular environment. Spatial transcriptomics (ST) addresses this limitation by enabling transcriptome-wide gene expression profiling while preserving spatial context. One of the principal challenges in ST data analysis is spatial clustering, which reveals spatial domains based on the spots within a tissue. Modern ST sequencing procedures typically include a high-resolution histology image, which has been shown in previous studies to be closely connected to gene expression profiles. However, current spatial clustering methods often fail to fully integrate high-resolution histology image features with gene expression data, limiting their ability to capture critical spatial and cellular interactions. In this study, we propose the spatial transcriptomics multi-modal clustering (stMMC) model, a novel contrastive learning-based deep learning approach that integrates gene expression data with histology image features through a multi-modal parallel graph autoencoder. We tested stMMC against four state-of-the-art baseline models: Leiden, GraphST, SpaGCN, and stLearn on two public ST datasets with 13 sample slices in total. The experiments demonstrated that stMMC outperforms all the baseline models in terms of ARI and NMI. An ablation study further validated the contributions of contrastive learning and the incorporation of histology image features.
Drug-target interaction (DTI) prediction is crucial for drug development and repositioning. Methods using heterogeneous graph neural networks (HGNNs) for DTI prediction have become a promising approach, with attention-based models often achieving excellent performance. However, these methods typically overlook edge features when dealing with heterogeneous biomedical networks. We propose a heterogeneous network-based contrastive learning method called HNCL-DTI, which designs a heterogeneous graph attention network to predict potential/novel DTIs. Specifically, our HNCL-DTI utilizes contrastive learning to collaboratively learn node representations from the perspective of both node-based and edge-based attention within the heterogeneous structure of biomedical networks. Experimental results show that HNCL-DTI outperforms existing advanced baseline methods on benchmark datasets, demonstrating strong predictive ability and practical effectiveness. The data and source code are available at https://github.com/Zaiwen/HNCL-DTI.
Unmanned aerial vehicle (UAV)-based bi-modal salient object detection (BSOD) aims to segment salient objects in a scene utilizing complementary cues in unaligned RGB and thermal image pairs. However, the high computational expense of existing UAV-based BSOD models limits their applicability to real-world UAV devices. To address this problem, we propose an efficient Fourier filter network with contrastive learning that achieves both real-time and accurate performance. Specifically, we first design a semantic contrastive alignment loss to align the two modalities at the semantic level, which facilitates mutual refinement in a parameter-free way. Second, inspired by the fast Fourier transform that obtains global relevance in linear complexity, we propose synchronized alignment fusion, which aligns and fuses bi-modal features in the channel and spatial dimensions by a hierarchical filtering mechanism. Our proposed model, AlignSal, reduces the number of parameters by 70.0%, decreases the floating point operations by 49.4%, and increases the inference speed by 152.5% compared to the cutting-edge BSOD model (i.e., MROS). Extensive experiments on the UAV RGB-T 2400 and seven bi-modal dense prediction datasets demonstrate that AlignSal achieves both real-time inference speed and better performance and generalizability compared to nineteen state-of-the-art models across most evaluation metrics. In addition, our ablation studies further verify AlignSal's potential in boosting the performance of existing aligned BSOD models on UAV-based unaligned data. The code is available at: https://github.com/JoshuaLPF/AlignSal.
Contrastive learning attempts to learn representations from un-labeled data; it does so via a loss function that encourages the embedding of a point to be close to that of its augmentations, and far from the embeddings of random other points. This simple idea performs remarkably well, yet it is not precisely theoretically understood why this is the case. In this paper we analyze contrastive learning (specifically, the InfoNCE loss) in a natural context: dimensionality reduction in Gaussian Mixture Models. Crucially, we define an augmentation of a data point as being another independent draw from the same underlying mixture component. We show that vanilla InfoNCE is able to find the optimal lower-dimensional subspace even when the Gaussians are not isotropic -- something that vanilla spectral techniques cannot do. We further extend our analyses to multi-modal contrastive learning algorithms (e.g., CLIP). In this setting we show that contrastive learning learns the subset of fisher-optimal subspace, effectively filtering out all the noise from the learnt representations.
Multi-modal contrastive learning with language supervision has presented a paradigm shift in modern machine learning. By pre-training on a web-scale dataset, multi-modal contrastive learning can learn high-quality representations that exhibit impressive robustness and transferability. Despite its empirical success, the theoretical understanding is still in its infancy, especially regarding its comparison with single-modal contrastive learning. In this work, we introduce a feature learning theory framework that provides a theoretical foundation for understanding the differences between multi-modal and single-modal contrastive learning. Based on a data generation model consisting of signal and noise, our analysis is performed on a ReLU network trained with the InfoMax objective function. Through a trajectory-based optimization analysis and generalization characterization on downstream tasks, we identify the critical factor, which is the signal-to-noise ratio (SNR), that impacts the generalizability in downstream tasks of both multi-modal and single-modal contrastive learning. Through the cooperation between the two modalities, multi-modal learning can achieve better feature learning, leading to improvements in performance in downstream tasks compared to single-modal learning. Our analysis provides a unified framework that can characterize the optimization and generalization of both single-modal and multi-modal contrastive learning. Empirical experiments on both synthetic and real-world datasets further consolidate our theoretical findings.
We present a method to detect departures from business-justified workflows among support agents. Our goal is to assist auditors in identifying agent actions that cannot be explained by the activity within their surrounding context, where normal activity patterns are established from historical data. We apply our method to help audit millions of actions of over three thousand support agents. We collect logs from the tools used by support agents and construct a bipartite graph of Actions and Entities representing all the actions of the agents, as well as background information about entities. From this graph, we sample subgraphs rooted on security-significant actions taken by the agents. Each subgraph captures the relevant context of the root action in terms of other actions, entities and their relationships. We then prioritize the rooted-subgraphs for auditor review using feed-forward and graph neural networks, as well as nearest neighbors techniques. To alleviate the issue of scarce labeling data, we use contrastive learning and domain-specific data augmentations. Expert auditors label the top ranked subgraphs as ``worth auditing" or ``not worth auditing" based on the company's business policies. This system finds subgraphs that are worth auditing with high enough precision to be used in production.
Semi-supervised learning (SSL) is a popular solution to alleviate the high annotation cost in medical image classification. As a main branch of SSL, consistency regularization engages in imposing consensus between the predictions of a single sample from different views, termed as Absolute Location consistency (AL-c). However, only AL-c may be insufficient. Just like when diagnosing a case in practice, besides the case itself, the doctor usually refers to certain related trustworthy cases to make more reliable decisions.Therefore, we argue that solely relying on AL-c may ignore the relative differences across samples, which we interpret as relative locations, and only exploit limited information from one perspective. To address this issue, we propose a Sample Consistency Mean Teacher (SCMT) which not only incorporates AL c but also additionally enforces consistency between the samples' relative similarities to its related samples, called Relative Location consistency (RL c). AL c and RL c conduct consistency regularization from two different perspectives, jointly extracting more diverse semantic information for classification. On the other hand, due to the highly similar structures in medical images, the sample distribution could be overly dense in feature space, making their relative locations susceptible to noise. To tackle this problem, we further develop a Sample Scatter Mean Teacher (SSMT) by utilizing contrastive learning to sparsify the sample distribution and obtain robust and effective relative locations. Extensive experiments on different datasets demonstrate the superiority of our method.
Graph Contrastive Learning (GCL) has recently emerged as a promising graph self-supervised learning framework for learning discriminative node representations without labels. The widely adopted objective function of GCL benefits from two key properties: \emph{alignment} and \emph{uniformity}, which align representations of positive node pairs while uniformly distributing all representations on the hypersphere. The uniformity property plays a critical role in preventing representation collapse and is achieved by pushing apart augmented views of different nodes (negative pairs). As such, existing GCL methods inherently rely on increasing the quantity and quality of negative samples, resulting in heavy computational demands, memory overhead, and potential class collision issues. In this study, we propose a negative-free objective to achieve uniformity, inspired by the fact that points distributed according to a normalized isotropic Gaussian are uniformly spread across the unit hypersphere. Therefore, we can minimize the distance between the distribution of learned representations and the isotropic Gaussian distribution to promote the uniformity of node representations. Our method also distinguishes itself from other approaches by eliminating the need for a parameterized mutual information estimator, an additional projector, asymmetric structures, and, crucially, negative samples. Extensive experiments over seven graph benchmarks demonstrate that our proposal achieves competitive performance with fewer parameters, shorter training times, and lower memory consumption compared to existing GCL methods.
As data privacy and security attract increasing attention, Federated Recommender System (FRS) offers a solution that strikes a balance between providing high-quality recommendations and preserving user privacy. However, the presence of statistical heterogeneity in FRS, commonly observed due to personalized decision-making patterns, can pose challenges. To address this issue and maximize the benefit of collaborative filtering (CF) in FRS, it is intuitive to consider clustering clients (users) as well as items into different groups and learning group-specific models. Existing methods either resort to client clustering via user representations-risking privacy leakage, or employ classical clustering strategies on item embeddings or gradients, which we found are plagued by the curse of dimensionality. In this paper, we delve into the inefficiencies of the K-Means method in client grouping, attributing failures due to the high dimensionality as well as data sparsity occurring in FRS, and propose CoFedRec, a novel Co-clustering Federated Recommendation mechanism, to address clients heterogeneity and enhance the collaborative filtering within the federated framework. Specifically, the server initially formulates an item membership from the client-provided item networks. Subsequently, clients are grouped regarding a specific item category picked from the item membership during each communication round, resulting in an intelligently aggregated group model. Meanwhile, to comprehensively capture the global inter-relationships among items, we incorporate an additional supervised contrastive learning term based on the server-side generated item membership into the local training phase for each client. Extensive experiments on four datasets are provided, which verify the effectiveness of the proposed CoFedRec.
In high-energy physics, particle jet tagging plays a pivotal role in distinguishing quark from gluon jets using data from collider experiments. While graph-based deep learning methods have advanced this task beyond traditional feature-engineered approaches, the complex data structure and limited labeled samples present ongoing challenges. However, existing contrastive learning (CL) frameworks struggle to leverage rationale-aware augmentations effectively, often lacking supervision signals that guide the extraction of salient features and facing computational efficiency issues such as high parameter counts. In this study, we demonstrate that integrating a quantum rationale generator (QRG) within our proposed Quantum Rationale-aware Graph Contrastive Learning (QRGCL) framework significantly enhances jet discrimination performance, reducing reliance on labeled data and capturing discriminative features. Evaluated on the quark-gluon jet dataset, QRGCL achieves an AUC score of $77.53\%$ while maintaining a compact architecture of only 45 QRG parameters, outperforming classical, quantum, and hybrid GCL and GNN benchmarks. These results highlight QRGCL's potential to advance jet tagging and other complex classification tasks in high-energy physics, where computational efficiency and feature extraction limitations persist.