Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

6111722 · Jun 202019922001200920172026
48 results for bipartite self-attention

Graph neural networks speed up nonnegative matrix factorization.

problem Efficiently factorize nonnegative matrices for various applications.
method Developed a graph neural network that combines bipartite self-attention with ADMM updates.
result Significant acceleration achieved in nonnegative matrix factorization.

Learning latent representations of nodes in graphs is an important and ubiquitous task with widespread applications such as link prediction, node classification, and graph visualization. Previous methods on graph representation learning mainly focus on static graphs, however, many real-world graphs are dynamic and evol…

2018-12-22abs ↗pdf ↗

Bipartite networks are a common type of network data in which there are two types of vertices, and only vertices of different types can be connected. While bipartite networks exhibit community structure like their unipartite counterparts, existing approaches to bipartite community detection have drawbacks, including im…

2014-03-12abs ↗pdf ↗

Self-attention prefers sparse functions of input sequences, reducing sample complexity.

problem Understanding the inductive biases of self-attention in modeling long-range dependencies.
method Theoretical analysis and synthetic experiments to probe sample complexity of learning sparse functions with Transformers.
result Bounded-norm Transformer networks can represent sparse functions of the input sequence with logarithmic sample complexity.

Self-attention models benefit equally from width and depth, but beyond a certain point, depth becomes less efficient.

problem Understanding the optimal balance between depth and width in self-attention models.
method Theoretical predictions and empirical ablations on networks of varying depths and widths.
result An optimal width of 30K is recommended for a 1-Trillion parameter network, marking a significant width for self-attention models.

Paper investigates Lipschitz constants of self-attention modules in neural networks.

problem Lipschitz constants of self-attention modules in neural networks.
method Proved standard dot-product self-attention is not Lipschitz for unbounded input domain. Proposed L2 self-attention that is Lipschitz. Derived upper bound on L2 self-attention's Lipschitz constant.
result Proved standard self-attention is not Lipschitz for unbounded input domain and proposed an alternative L2 self-attention that is Lipschitz.

New model for detecting communities in weighted bipartite networks.

problem No model for community detection in overlapping bipartite weighted networks.
method Introduces BiMMDF model allowing any distribution with block structure.
result Efficient algorithm with theoretical guarantee of consistent estimation.

Kernel PCA explains self-attention mechanisms in deep learning models.

problem Understanding and explaining self-attention mechanisms in deep learning models.
method Deriving self-attention from kernel principal component analysis (kernel PCA).
result RPC-Attention, a robust attention mechanism, outperforms softmax attention in various tasks.

Study reveals self-attention's role in learning and generalizing interactions.

problem Understanding self-attention's theoretical role in neural architectures.
method Interacting entities analysis, including multi-agent RL and genetic sequences.
result Self-attention efficiently represents, learns, and generalizes pairwise interactions.

Linformer reduces transformer complexity to linear, improving efficiency.

problem High cost of training and deploying large transformer models for long sequences.
method Approximates self-attention with low-rank matrix, proposing Linformer with O(n)O(n) complexity.
result Linformer performs similarly to standard transformers but is more memory- and time-efficient.

Skeinformer accelerates self-attention for long sequences with linear complexity.

problem Efficiency of Transformer models in processing long sequences.
method Matrix sketching and column sampling to reduce quadratic complexity to linear.
result Skeinformer outperforms alternatives with smaller time/space footprint.

Paper connects MoE and self-attention, proposing active-attention.

problem Improving efficiency and performance of self-attention mechanisms.
method Established connection between MoE and self-attention, analyzed quadratic gating functions, proposed active-attention mechanism.
result Active-attention outperforms standard self-attention in various tasks.

Gradient descent converges geometrically to optimal self-attention parameters.

problem Training softmax self-attention layers for linear regression.
method Structure-aware gradient descent with preconditioner and regularizer.
result Gradient descent converges geometrically to global minima.

We present a simple combinatorial model for quasipositive surfaces and positive braids, based on embedded bipartite graphs. As a first application, we extend the well-known duality on standard diagrams of torus links to twisted torus links. We then introduce a combinatorial notion of adjacency for bipartite graph links…

2011-11-16abs ↗pdf ↗

We present evidence in support of a conjecture that a bipartite graph with at least five vertices in each part and |E(G)| \geq 4 |V(G)| - 17 is intrinsically knotted. We prove the conjecture for graphs that have exactly five or exactly six vertices in one part. We also show that there is a constant C_n such that a bipa…

2008-10-31abs ↗pdf ↗

Develops a new variational estimator for node popularity in bipartite networks.

problem Estimating node popularity in bipartite networks with varying patterns.
method Variational Expectation-Maximization (VEM) framework for the Two-Way Node Popularity Model (TNPM).
result The proposed method achieves superior estimation accuracy across different types of networks.

Improved text summarization using belief propagation on weighted bipartite graphs.

problem Text summarization from a graph theory perspective.
method Generalized belief propagation algorithm for weighted bipartite graphs.
result Our algorithm outperforms greedy methods in text summarization tasks.

New method for matching bipartite and unipartite graphs without collapsing.

problem Matching between bipartite and unipartite networks without losing information.
method Formulated as an undirected graphical model, aligns graphs without collapsing.
result Consistent method with conditions for exact recovery of matching solution.

Incorrect parity-based descriptions of realizable Gauss diagrams found, but bipartite graphs provide a valid approach.

problem Incorrect descriptions of realizable Gauss diagrams using parity conditions.
method Used bipartite graphs to describe realizable Gauss diagrams.
result Realizable Gauss diagrams can be accurately described using bipartite graphs.

MCSAE improves speaker embedding by focusing on both high- and low-level features.

problem Reduced effect of low-level features in speaker embedding encoding.
method Masked cross self-attentive encoding using ResNet with multi-layer aggregation and random masking regularization.
result Improved speaker embedding with equal error rate of 2.63% and minimum detection cost function of 0.1453.

Transformers' self-attention mechanism is mapped to a generalized Potts model.

problem Uncertainty in what type of data distribution self-attention can efficiently learn.
method Decouple word positions and embeddings, then show self-attention learns a generalized Potts model.
result Training self-attention is equivalent to solving the inverse Potts problem.

A new model detects common patterns in pollination networks.

problem Comparing organization of bipartite networks to understand community structure.
method colBiSBM, a family of probabilistic models for collections of bipartite networks.
result The method uncovers shared ecological roles and partitions networks.

New analysis shows how attention masks and LayerNorm prevent rank collapse in transformers.

problem Rank collapse in transformer models with increasing depth.
method General analysis of rank collapse under self-attention, considering attention masks and LayerNorm.
result Self-attention with LayerNorm can prevent rank collapse and maintain a rich set of equilibria.

A graph is intrinsically knotted if every embedding contains a knotted cycle. It is known that intrinsically knotted graphs have at least 21 edges and that the KS graphs, K7K_7 and the 13 graphs obtained from K7K_7 by Y\nabla Y moves, are the only minor minimal intrinsically knotted graphs with 21 edges. This set incl…

2014-11-07abs ↗pdf ↗