Related papers: A Fresh Take on Stale Embeddings: Improving Dense …
We consider the densest submatrix problem, which seeks the submatrix of fixed size of a given binary matrix that contains the most nonzero entries. This problem is a natural generalization of fundamental problems in combinatorial…
It is known that training deep neural networks, in particular, deep convolutional networks, with aggressively reduced numerical precision is challenging. The stochastic gradient descent algorithm becomes unstable in the presence of noisy…
The use of deep learning has successfully solved several problems in the field of medical imaging. Deep learning has been applied to the CT denoising problem successfully. However, the use of deep learning requires large amounts of data to…
A good supervised embedding for a specific machine learning task is only sensitive to changes in the label of interest and is invariant to other confounding factors. We leverage the concept of repeatability from measurement theory to…
Sparse document representations have been widely used to retrieve relevant documents via exact lexical matching. Owing to the pre-computed inverted index, it supports fast ad-hoc search but incurs the vocabulary mismatch problem. Although…
Class imbalance is a problem of significant importance in applied deep learning where trained models are exploited for decision support and automated decisions in critical areas such as health and medicine, transportation, and finance. The…
Multimodal chest X-Ray analysis often fine-tunes large vision-language models, which is computationally costly. We study parameter-efficient training (PET) strategies, including frozen encoders, BitFit, LoRA, and adapters for multi-label…
This technical report presents the training methodology and evaluation results of the open-source dewey_en_beta embedding model. The increasing demand for retrieval-augmented generation (RAG) systems and the expanding context window…
The ability to reconstruct fine-grained network session data, including individual packets, from coarse-grained feature vectors is crucial for improving network security models. However, the large-scale collection and storage of raw network…
Social network alignment aims at aligning person identities across social networks. Embedding based models have been shown effective for the alignment where the structural proximity preserving objective is typically adopted for the model…
Deep neural networks are capable of modelling highly non-linear functions by capturing different levels of abstraction of data hierarchically. While training deep networks, first the system is initialized near a good optimum by greedy…
Real-world applications of neural language models often involve running many different models over the same corpus. The high computational cost of these runs has led to interest in techniques that can reuse the contextualized embeddings…
Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…
Deep neural networks can be effective means to automatically classify aerial images but is easy to overfit to the training data. It is critical for trained neural networks to be robust to variations that exist between training and test…
Learned sparse text embeddings have gained popularity due to their effectiveness in top-k retrieval and inherent interpretability. Their distributional idiosyncrasies, however, have long hindered their use in real-world retrieval systems.…
Fine-grained annotations---e.g. dense image labels, image segmentation and text tagging---are useful in many ML applications but they are labor-intensive to generate. Moreover there are often systematic, structured errors in these…
Deep neural networks are learning models with a very high capacity and therefore prone to over-fitting. Many regularization techniques such as Dropout, DropConnect, and weight decay all attempt to solve the problem of over-fitting by…
A significant research problem of recent interest is the localization of targets like vessels, surgical needles, and tumors in photoacoustic (PA) images. To achieve accurate localization, a high photoacoustic signal-to-noise ratio (SNR) is…
Learning continuous representations of discrete objects such as text, users, movies, and URLs lies at the heart of many applications including language and user modeling. When using discrete objects as input to neural networks, we often…
Computational cost of training state-of-the-art deep models in many learning problems is rapidly increasing due to more sophisticated models and larger datasets. A recent promising direction for reducing training cost is dataset…