Search Results for author:
Found 44 papers, 21 papers with code
The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation
Based on this phenomenon and interpretation, we further propose a method that includes two plug-and-play modules: one to flatten the loss landscapes for low-level features during source-domain training as a novel sharpness-aware minimization method, and the other to directly supplement target-domain information to the model during target-domain testing by low-level-based calibration.
Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization
If an input is fully utilized by the network, {it generally matches these directions (e. g., a portion of a hypersphere), resulting in a representation with a high norm.
Intrinsic and Extrinsic Factor Disentanglement for Recommendation in Various Context Scenarios
In recommender systems, the patterns of user behaviors (e. g., purchase, click) may vary greatly in different contexts (e. g., time and location).
Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables
Retrieval-augmented generation (RAG) is a key technique for leveraging external knowledge and reducing hallucinations in large language models (LLMs).
Progressive Collaborative and Semantic Knowledge Fusion for Generative Recommendation
In the second stage, we propose an in-modality knowledge distillation task, designed to effectively capture and integrate knowledge from both semantic and collaborative modalities.
Resource-Constrained Federated Continual Learning: What Does Matter?
We revisit this problem with a large-scale benchmark and analyze the performance of state-of-the-art FCL approaches under different resource-constrained settings.
Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models
The recent advancement of Multimodal Large Language Models (MLLMs) has significantly improved their fine-grained perception of single images and general comprehension across multiple images.
Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot Learning
We find that MAE tends to focus on low-level domain information during reconstructing pixels while changing the reconstruction target to token features could mitigate this problem.
FedGIG: Graph Inversion from Gradient in Federated Learning
Recent studies have shown that Federated learning (FL) is vulnerable to Gradient Inversion Attacks (GIA), which can recover private training data from shared gradients.
Rehearsal-Free Continual Federated Learning with Synergistic Regularization
Specifically, we first apply traditional regularization techniques to CFL and observe that existing regularization techniques, especially synaptic intelligence, can achieve promising results under homogeneous data distribution but fail when the data is heterogeneous.
Unleashing the Power of Continual Learning on Non-Centralized Devices: A Survey
To achieve high reliability and scalability in deploying this paradigm in distributed systems, it is essential to conquer challenges stemming from both spatial and temporal dimensions, manifesting as distribution shifts, catastrophic forgetting, heterogeneity, and privacy issues.
Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation
Cross-domain few-shot segmentation (CD-FSS) is proposed to first pre-train the model on a large-scale source-domain dataset, and then transfer the model to data-scarce target-domain datasets for pixel-level segmentation.
Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalization
In the optimization objectives of these methods, spurious features are still distinguished from plain noise, which hinders the discovery of causal rationales.
Mixed-Precision Embeddings for Large-Scale Recommendation Models
Specifically, to reduce the size of the search space, we first group features by frequency and then search precision for each feature group.
PAGE: Parametric Generative Explainer for Graph Neural Network
Due to the dimensionality reduction of features in the latent space of the auto-encoder, it becomes easier to extract causal features leading to the model's output, which can be easily employed to generate explanations.
Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-Shot Open-Set Recognition
Few-shot open-set recognition (FSOR) is a challenging task that requires a model to recognize known classes and identify unknown classes with limited labeled data.
MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning
Humans exhibit a remarkable ability to learn quickly from a limited number of labeled samples, a capability that starkly contrasts with that of current machine learning systems.
Adversarial Attack for Explanation Robustness of Rationalization Models
Based on this, we make a series of recommendations for improving rationalization models in terms of explanation.
Masked Random Noise for Communication Efficient Federated Learning
For this purpose, we propose Federated Masked Random Noise (FedMRN), a novel framework that enables clients to learn a 1-bit mask for each model parameter and apply masked random noise (i. e., the Hadamard product of random noise and masks) to represent model updates.
FedBAT: Communication-Efficient Federated Learning via Learnable Binarization
To this end, we propose Federated Binarization-Aware Training (FedBAT), a novel framework that directly learns binary model updates during the local training process, thus inherently reducing the approximation errors.
Embedding Compression in Recommender Systems: A Survey
In this survey, we provide a comprehensive review of embedding compression approaches in recommender systems.
Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching
Then, the client can choose to adopt a new initial model or a previous model with similar knowledge to train the new task and simultaneously migrate knowledge from previous tasks based on these correlations.
Compositional Few-Shot Class-Incremental Learning
Few-shot class-incremental learning (FSCIL) is proposed to continually learn from novel classes with only a few samples after the (pre-)training on base classes with sufficient data.
class-incremental learning
Few-Shot Class-Incremental Learning
+1
Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learning
We first interpret the confusion as the collision between the novel-class and the base-class region in the feature space.
class-incremental learning
Few-Shot Class-Incremental Learning
+1
A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective
As the ultimate goal of GFMs is to learn generalized graph knowledge, we provide a comprehensive survey of self-supervised GFMs from a novel knowledge-based perspective.
Towards Efficient Replay in Federated Incremental Learning
Then, the client trains the local model with both the cached samples and the samples from the new task.
Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning
To enhance the transferability and facilitate fine-tuning, we introduce a simple yet effective approach to achieve long-range flattening of the minima in the loss landscape.
Masked Graph Autoencoder with Non-discrete Bandwidths
Inspired by these understandings, we explore non-discrete edge masks, which are sampled from a continuous and dispersive probability distribution instead of the discrete Bernoulli distribution.
Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling
Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available.
Enhancing the Rationale-Input Alignment for Self-explaining Rationalization
Rationalization empowers deep learning models with self-explaining capabilities through a cooperative game, where a generator selects a semantically consistent subset of the input as a rationale, and a subsequent predictor makes predictions based on the selected rationale.
D-Separation for Causal Self-Explanation
Instead of attempting to rectify the issues of the MMI criterion, we propose a novel criterion to uncover the causal rationale, termed the Minimum Conditional Dependence (MCD) criterion, which is grounded on our finding that the non-causal features and the target label are \emph{d-separated} by the causal rationale.
Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint
However, such a cooperative game may incur the degeneration problem where the predictor overfits to the uninformative pieces generated by a not yet well-trained generator and in turn, leads the generator to converge to a sub-optimal model that tends to select senseless pieces.
MGR: Multi-generator Based Rationalization
Rationalization is to employ a generator and a predictor to construct a self-explaining NLP model in which the generator selects a subset of human-intelligible pieces of the input text to the following predictor.
CSGCL: Community-Strength-Enhanced Graph Contrastive Learning
Graph Contrastive Learning (GCL) is an effective way to learn generalized graph representations in a self-supervised manner, and has grown rapidly in recent years.
Structure Diagram Recognition in Financial Announcements
Accurately extracting structured data from structure diagrams in financial announcements is of great practical importance for building financial knowledge graphs and further improving the efficiency of various financial applications.
DaFKD: Domain-Aware Federated Knowledge Distillation
In this paper, we propose a new perspective that treats the local data in each client as a specific domain and design a novel domain knowledge aware federated distillation method, dubbed DaFKD, that can discern the importance of each model to the distillation sample, and thus is able to optimize the ensemble of soft predictions from diverse models.
Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction
To this end, we formulate a novel quantization training paradigm to compress the embeddings from the training stage, termed low-precision training (LPT).
Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation
Few-shot class-incremental learning (FSCIL) is designed to incrementally recognize novel classes with only few training samples after the (pre-)training on base classes with sufficient samples, which focuses on both base-class performance and novel-class generalization.
class-incremental learning
Few-Shot Class-Incremental Learning
+1
FR: Folded Rationalization with a Unified Encoder
Conventional works generally employ a two-phase model in which a generator selects the most important pieces, followed by a predictor that makes predictions based on the selected pieces.
Hierarchical Local-Global Transformer for Temporal Sentence Grounding
To address this issue, in this paper, we propose a novel Hierarchical Local-Global Transformer (HLGT) to leverage this hierarchy information and model the interactions between different levels of granularity and different modalities for learning more fine-grained multi-modal representations.
SNEAK: Synonymous Sentences-Aware Adversarial Attack on Natural Language Video Localization
Natural language video localization (NLVL) is an important task in the vision-language understanding area, which calls for an in-depth understanding of not only computer vision and natural language side alone, but more importantly the interplay between both sides.
Intermittent Pulling with Local Compensation for Communication-Efficient Federated Learning
A major bottleneck on the performance of distributed Stochastic Gradient Descent (SGD) algorithm for large-scale Federated Learning is the communication overhead on pushing local gradients and pulling global model.
Gradient Scheduling with Global Momentum for Non-IID Data Distributed Asynchronous Training
Distributed asynchronous offline training has received widespread attention in recent years because of its high performance on large-scale data and complex models.
AccUDNN: A GPU Memory Efficient Accelerator for Training Ultra-deep Neural Networks
Typically, Ultra-deep neural network(UDNN) tends to yield high-quality model, but its training process is usually resource intensive and time-consuming.
